Text Arena Creative Writing: LMArena Text Arena - Creative Writing
Crowdsourced human-preference leaderboard for text models run by LMArena, restricted to the Creative Writing category of the Text arena (no style control). Voters compare two anonymous responses to a creative-writing prompt and pick the better one; ratings use a Bradley-Terry model scaled like Elo, with 95% confidence intervals. Higher is better.
Configurations
270
tracked on this benchmark
Score band
1534.0 – 863.0
best → lowest tracked
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by Elo (higher is better).
Configuration: Claude Opus 5.5 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 5.5 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 1 of 416, rating 1534.2 (95% CI 1520.6-1547.8), 2453 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 4 Argon (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 4 Argon (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 2 of 416, rating 1523.1 (95% CI 1509.6-1536.5), 2335 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Fable 5.1 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Fable 5.1 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 3 of 416, rating 1509.7 (95% CI 1498.9-1520.6), 3729 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 5 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 5 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 5 of 416, rating 1494.6 (95% CI 1486.7-1502.6), 7903 votes. Other board entries for this model, not used: 'Claude Opus 5 (High)' 1486.5 (rank 10). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Fable 5 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Fable 5 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 6 of 416, rating 1493.4 (95% CI 1486.2-1500.7), 9586 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Wonder (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Wonder (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 7 of 416, rating 1492.6 (95% CI 1475.7-1509.6), 1350 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.8 Flash (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.8 Flash (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 8 of 416, rating 1489.4 (95% CI 1481.9-1496.8), 9817 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.7 Flash (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.7 Flash (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 9 of 416, rating 1489.1 (95% CI 1480.7-1497.6), 6770 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 4.6
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 4.6' (category creative_writing in text/latest-00000-of-00001.parquet): rank 12 of 416, rating 1483.7 (95% CI 1477.8-1489.7), 15623 votes. Other board entries for this model, not used: 'Claude Opus 4.6 (High)' 1504.8 (rank 4). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3 Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3 Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 13 of 416, rating 1482.5 (95% CI 1474.4-1490.5), 6542 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.1 Pro Preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.1 Pro Preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 14 of 416, rating 1481.8 (95% CI 1476.6-1487.1), 24371 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 4.7
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 4.7' (category creative_writing in text/latest-00000-of-00001.parquet): rank 15 of 416, rating 1479.7 (95% CI 1472.9-1486.6), 12036 votes. Other board entries for this model, not used: 'Claude Opus 4.7 (High)' 1486.2 (rank 11). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Sonnet 5.5 (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Sonnet 5.5 (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 18 of 416, rating 1468.3 (95% CI 1454.2-1482.4), 2058 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.5 Flash (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.5 Flash (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 19 of 416, rating 1467.6 (95% CI 1460.4-1474.8), 9477 votes. Other board entries for this model, not used: 'Gemini 3.5 Flash (Medium)' 1470.1 (rank 17). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2.6-Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.6-Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 20 of 416, rating 1466.4 (95% CI 1445.4-1487.5), 792 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.6 Flash (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.6 Flash (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 21 of 416, rating 1466.1 (95% CI 1458.1-1474.0), 7584 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Spark 1.3 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Spark 1.3 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 23 of 416, rating 1462.4 (95% CI 1452.6-1472.3), 4562 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5.2 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5.2 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 24 of 416, rating 1461.6 (95% CI 1454.8-1468.5), 10456 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5.3 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5.3 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 25 of 416, rating 1459.2 (95% CI 1450.4-1468.0), 5741 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Spark
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Spark' (category creative_writing in text/latest-00000-of-00001.parquet): rank 26 of 416, rating 1458.7 (95% CI 1445.1-1472.3), 2047 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3 Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3 Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 27 of 416, rating 1456.8 (95% CI 1447.6-1466.0), 4833 votes. Other board entries for this model, not used: 'Gemini 3 Flash (Minimal)' 1435.2 (rank 55). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K3 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K3 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 28 of 416, rating 1456.2 (95% CI 1448.3-1464.2), 7248 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 4.8 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 4.8 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 30 of 416, rating 1454.4 (95% CI 1447.9-1461.0), 12810 votes. Other board entries for this model, not used: 'Claude Opus 4.8' 1446.4 (rank 36). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 2.5 Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 2.5 Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 31 of 416, rating 1453.7 (95% CI 1448.6-1458.7), 17700 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 32 of 416, rating 1452.6 (95% CI 1446.3-1458.9), 12807 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 33 of 416, rating 1452.3 (95% CI 1445.7-1458.8), 13417 votes. Other board entries for this model, not used: 'GPT-5.5 (High)' 1455.3 (rank 29). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.6 Sol (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.6 Sol (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 34 of 416, rating 1450.2 (95% CI 1442.8-1457.7), 8988 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V4-Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V4-Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 37 of 416, rating 1446.2 (95% CI 1438.9-1453.4), 9731 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 4.5 (20251101)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 4.5 (20251101)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 39 of 416, rating 1443.0 (95% CI 1436.7-1449.4), 11407 votes. Other board entries for this model, not used: 'Claude Opus 4.5 (High, 32K, 20251101)' 1444.8 (rank 38). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 40 of 416, rating 1441.8 (95% CI 1434.2-1449.4), 8288 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Sonnet 4.5 (20250929)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Sonnet 4.5 (20250929)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 41 of 416, rating 1441.6 (95% CI 1435.6-1447.5), 12417 votes. Other board entries for this model, not used: 'Claude Sonnet 4.5 (High, 32K, 20250929)' 1424.6 (rank 64). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: ERNIE 5.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'ERNIE 5.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 42 of 416, rating 1440.9 (95% CI 1432.6-1449.1), 6457 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5.3-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5.3-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 44 of 416, rating 1440.8 (95% CI 1433.1-1448.5), 8207 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V4-Pro (High, 20260813)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V4-Pro (High, 20260813)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 46 of 416, rating 1438.6 (95% CI 1424.8-1452.4), 1996 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V4.1-Flash-20260910 (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V4.1-Flash-20260910 (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 47 of 416, rating 1438.5 (95% CI 1426.7-1450.3), 2830 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.7-Plus
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.7-Plus' (category creative_writing in text/latest-00000-of-00001.parquet): rank 49 of 416, rating 1438.0 (95% CI 1430.4-1445.6), 7839 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2.5-Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.5-Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 50 of 416, rating 1438.0 (95% CI 1431.9-1444.1), 14635 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 51 of 416, rating 1437.9 (95% CI 1429.0-1446.8), 4859 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.20 Multi-Agent Beta (0309)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.20 Multi-Agent Beta (0309)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 52 of 416, rating 1436.2 (95% CI 1429.5-1443.0), 11296 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Sonnet 4.6
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Sonnet 4.6' (category creative_writing in text/latest-00000-of-00001.parquet): rank 53 of 416, rating 1435.4 (95% CI 1428.9-1441.8), 12386 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.6-Max-Preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.6-Max-Preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 54 of 416, rating 1435.3 (95% CI 1413.0-1457.7), 757 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Spark 1.2 (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Spark 1.2 (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 56 of 416, rating 1434.7 (95% CI 1421.2-1448.2), 2219 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Spark 1.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Spark 1.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 57 of 416, rating 1434.6 (95% CI 1427.5-1441.7), 9741 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K2.6
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K2.6' (category creative_writing in text/latest-00000-of-00001.parquet): rank 58 of 416, rating 1433.6 (95% CI 1425.4-1441.8), 6329 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.20 Beta (Reasoning, 0309)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.20 Beta (Reasoning, 0309)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 59 of 416, rating 1432.0 (95% CI 1425.3-1438.7), 11437 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.6 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.6 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 60 of 416, rating 1427.9 (95% CI 1419.8-1436.1), 7194 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.4
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 61 of 416, rating 1427.7 (95% CI 1421.0-1434.5), 11336 votes. Other board entries for this model, not used: 'GPT-5.4 (High)' 1439.0 (rank 45). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.1 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.1 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 62 of 416, rating 1427.1 (95% CI 1419.1-1435.1), 6243 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Other board entries for this model, not used: 'GPT-5.1' 1403.5 (rank 89). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: ERNIE 5.0 (0110)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'ERNIE 5.0 (0110)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 63 of 416, rating 1426.2 (95% CI 1418.1-1434.3), 5765 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-6.1 Sol (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-6.1 Sol (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 65 of 416, rating 1424.4 (95% CI 1409.7-1439.2), 1871 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K2.5 (Thinking)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K2.5 (Thinking)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 67 of 416, rating 1422.1 (95% CI 1416.0-1428.3), 12271 votes. Other board entries for this model, not used: 'Kimi K2.5 (Instant)' 1382.4 (rank 129). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.5 Flash-Lite
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.5 Flash-Lite' (category creative_writing in text/latest-00000-of-00001.parquet): rank 68 of 416, rating 1420.6 (95% CI 1412.7-1428.6), 7475 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-6 Astra (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-6 Astra (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 69 of 416, rating 1420.5 (95% CI 1409.0-1432.0), 3150 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.5 Instant
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.5 Instant' (category creative_writing in text/latest-00000-of-00001.parquet): rank 70 of 416, rating 1418.2 (95% CI 1408.6-1427.8), 4357 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-5V-Turbo
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-5V-Turbo' (category creative_writing in text/latest-00000-of-00001.parquet): rank 71 of 416, rating 1417.7 (95% CI 1403.7-1431.8), 1968 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Sonnet 5 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Sonnet 5 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 73 of 416, rating 1416.0 (95% CI 1409.1-1422.9), 10786 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 4 31B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 4 31B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 74 of 416, rating 1416.0 (95% CI 1397.3-1434.6), 971 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2-Pro
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2-Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 75 of 416, rating 1415.3 (95% CI 1405.2-1425.4), 3738 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.6 Terra (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.6 Terra (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 77 of 416, rating 1413.0 (95% CI 1405.8-1420.1), 9947 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.6
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.6' (category creative_writing in text/latest-00000-of-00001.parquet): rank 79 of 416, rating 1411.7 (95% CI 1403.3-1420.2), 5149 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Step 5 Preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Step 5 Preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 80 of 416, rating 1411.4 (95% CI 1397.7-1425.2), 2061 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 81 of 416, rating 1411.0 (95% CI 1404.4-1417.6), 10078 votes. Other board entries for this model, not used: 'Grok 4.1 (Thinking)' 1403.5 (rank 90). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Opus 4.1 (20250805)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Opus 4.1 (20250805)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 82 of 416, rating 1410.4 (95% CI 1404.2-1416.6), 10881 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Other board entries for this model, not used: 'Claude Opus 4.1 (Thinking 16K, 20250805)' 1412.0 (rank 78). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-R1 (0528)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-R1 (0528)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 84 of 416, rating 1405.3 (95% CI 1392.8-1417.7), 2409 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: ChatGPT-4o Latest (20250326)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'ChatGPT-4o Latest (20250326)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 85 of 416, rating 1405.0 (95% CI 1399.1-1410.9), 11530 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Hy3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Hy3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 86 of 416, rating 1404.8 (95% CI 1392.8-1416.8), 2655 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2.6-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.6-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 87 of 416, rating 1404.3 (95% CI 1392.1-1416.4), 2741 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.6-Plus
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.6-Plus' (category creative_writing in text/latest-00000-of-00001.parquet): rank 88 of 416, rating 1403.7 (95% CI 1395.8-1411.5), 7215 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V4-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V4-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 93 of 416, rating 1402.9 (95% CI 1395.4-1410.3), 8579 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiniMax-M3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 94 of 416, rating 1402.7 (95% CI 1396.2-1409.1), 12398 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.5-397B-A17B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.5-397B-A17B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 95 of 416, rating 1402.5 (95% CI 1396.9-1408.0), 17199 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.7
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.7' (category creative_writing in text/latest-00000-of-00001.parquet): rank 96 of 416, rating 1401.3 (95% CI 1388.2-1414.4), 1961 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 4 26B A4B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 4 26B A4B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 97 of 416, rating 1401.2 (95% CI 1383.0-1419.3), 1000 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 3.1 Flash-Lite Preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 3.1 Flash-Lite Preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 99 of 416, rating 1401.0 (95% CI 1394.2-1407.8), 10590 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 2.5 Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 2.5 Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 102 of 416, rating 1399.9 (95% CI 1394.9-1404.8), 17647 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3.2
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3.2' (category creative_writing in text/latest-00000-of-00001.parquet): rank 103 of 416, rating 1399.4 (95% CI 1391.9-1407.0), 6884 votes. Other board entries for this model, not used: 'DeepSeek-V3.2 (Thinking)' 1389.3 (rank 119). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4 (0709)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4 (0709)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 106 of 416, rating 1396.6 (95% CI 1388.2-1405.0), 5346 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.6 Luna (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.6 Luna (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 107 of 416, rating 1395.9 (95% CI 1388.4-1403.3), 8692 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 108 of 416, rating 1395.1 (95% CI 1384.3-1405.9), 3094 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.1 Fast (Reasoning)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.1 Fast (Reasoning)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 109 of 416, rating 1394.4 (95% CI 1387.7-1401.1), 9004 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4.5 Preview (2025-02-27)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4.5 Preview (2025-02-27)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 110 of 416, rating 1393.6 (95% CI 1381.6-1405.5), 2618 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Hunyuan T1 (20250711)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Hunyuan T1 (20250711)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 111 of 416, rating 1393.1 (95% CI 1369.4-1416.9), 616 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 112 of 416, rating 1392.5 (95% CI 1384.8-1400.3), 7903 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2-Omni
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2-Omni' (category creative_writing in text/latest-00000-of-00001.parquet): rank 113 of 416, rating 1392.2 (95% CI 1381.5-1402.9), 3449 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Beam 1.0 501B A23B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Beam 1.0 501B A23B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 114 of 416, rating 1391.0 (95% CI 1371.3-1410.6), 968 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3.1-Terminus (Thinking)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3.1-Terminus (Thinking)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 115 of 416, rating 1390.8 (95% CI 1363.1-1418.5), 435 votes. Other board entries for this model, not used: 'DeepSeek-V3.1-Terminus' 1403.4 (rank 91). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Inkling
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Inkling' (category creative_writing in text/latest-00000-of-00001.parquet): rank 117 of 416, rating 1389.9 (95% CI 1382.6-1397.1), 9441 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3.2-Exp (Thinking)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3.2-Exp (Thinking)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 120 of 416, rating 1388.0 (95% CI 1370.7-1405.3), 1194 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Other board entries for this model, not used: 'DeepSeek-V3.2-Exp' 1403.2 (rank 92). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 122 of 416, rating 1387.7 (95% CI 1374.3-1401.1), 1975 votes. Other board entries for this model, not used: 'DeepSeek-V3.1 (Thinking)' 1400.9 (rank 101). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Large 3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large 3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 123 of 416, rating 1386.7 (95% CI 1381.3-1392.2), 15748 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4 Fast (Non-Reasoning)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4 Fast (Non-Reasoning)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 125 of 416, rating 1386.3 (95% CI 1366.3-1406.2), 889 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-235B-A22B-Thinking (2507)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-235B-A22B-Thinking (2507)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 127 of 416, rating 1383.6 (95% CI 1365.9-1401.2), 1083 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.8-27B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.8-27B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 128 of 416, rating 1382.9 (95% CI 1373.9-1392.0), 5342 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.7 (xHigh)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.7 (xHigh)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 130 of 416, rating 1381.2 (95% CI 1369.9-1392.5), 3337 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-Max (2025-09-23)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-Max (2025-09-23)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 131 of 416, rating 1380.6 (95% CI 1363.6-1397.6), 1152 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4.3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 132 of 416, rating 1379.8 (95% CI 1373.3-1386.2), 13224 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 4 Fast (Reasoning)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4 Fast (Reasoning)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 133 of 416, rating 1378.0 (95% CI 1366.2-1389.8), 2491 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-6 Sol (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-6 Sol (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 134 of 416, rating 1377.4 (95% CI 1365.9-1389.0), 3130 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiMo-V2-Flash (Non-Thinking)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2-Flash (Non-Thinking)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 135 of 416, rating 1376.1 (95% CI 1368.8-1383.4), 7347 votes. Other board entries for this model, not used: 'MiMo-V2-Flash (Thinking)' 1347.8 (rank 168). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.2 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.2 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 136 of 416, rating 1376.1 (95% CI 1368.8-1383.4), 7662 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Other board entries for this model, not used: 'GPT-5.2' 1375.7 (rank 137). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-235B-A22B-Instruct (2507)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-235B-A22B-Instruct (2507)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 139 of 416, rating 1374.7 (95% CI 1369.3-1380.1), 13888 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Medium 3.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Medium 3.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 141 of 416, rating 1373.9 (95% CI 1360.2-1387.5), 2073 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K2 Thinking Turbo
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K2 Thinking Turbo' (category creative_writing in text/latest-00000-of-00001.parquet): rank 142 of 416, rating 1373.4 (95% CI 1366.9-1380.0), 9528 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Haiku 4.5 (20251001)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Haiku 4.5 (20251001)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 143 of 416, rating 1370.8 (95% CI 1366.2-1375.4), 26153 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.4 mini (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.4 mini (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 144 of 416, rating 1370.2 (95% CI 1363.3-1377.1), 10822 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.5-122B-A10B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.5-122B-A10B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 146 of 416, rating 1368.1 (95% CI 1358.9-1377.3), 4519 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-VL-235B-A22B-Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-VL-235B-A22B-Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 148 of 416, rating 1366.0 (95% CI 1349.2-1382.7), 1354 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5 Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5 Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 149 of 416, rating 1364.7 (95% CI 1355.3-1374.2), 4014 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 150 of 416, rating 1364.2 (95% CI 1354.7-1373.7), 4244 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3 (0324)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3 (0324)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 151 of 416, rating 1363.9 (95% CI 1355.9-1371.9), 5990 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Large 4
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large 4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 152 of 416, rating 1363.8 (95% CI 1350.9-1376.6), 2383 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4.1 (2025-04-14)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4.1 (2025-04-14)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 153 of 416, rating 1363.4 (95% CI 1355.8-1371.1), 6655 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-6 Luna (Max)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-6 Luna (Max)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 154 of 416, rating 1362.7 (95% CI 1356.3-1369.1), 16380 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.5-27B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.5-27B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 155 of 416, rating 1362.6 (95% CI 1353.2-1371.9), 4297 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o3 (2025-04-16)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o3 (2025-04-16)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 157 of 416, rating 1358.4 (95% CI 1351.2-1365.7), 7632 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 159 of 416, rating 1358.3 (95% CI 1350.8-1365.9), 6621 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Step-3.5-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Step-3.5-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 160 of 416, rating 1357.2 (95% CI 1350.5-1363.9), 9784 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-235B-A22B (Non-Thinking)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-235B-A22B (Non-Thinking)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 161 of 416, rating 1356.2 (95% CI 1347.2-1365.3), 4569 votes. Other board entries for this model, not used: 'Qwen3-235B-A22B' 1316.1 (rank 209). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.3 Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.3 Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 162 of 416, rating 1355.2 (95% CI 1346.5-1363.8), 5350 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiniMax-M2.7
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M2.7' (category creative_writing in text/latest-00000-of-00001.parquet): rank 163 of 416, rating 1354.2 (95% CI 1348.2-1360.2), 15100 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-R1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-R1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 164 of 416, rating 1354.0 (95% CI 1343.7-1364.2), 3289 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K2 Preview (0905)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K2 Preview (0905)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 166 of 416, rating 1349.5 (95% CI 1334.2-1364.7), 1481 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.6V
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.6V' (category creative_writing in text/latest-00000-of-00001.parquet): rank 169 of 416, rating 1347.4 (95% CI 1319.4-1375.5), 425 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.5-35B-A3B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.5-35B-A3B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 170 of 416, rating 1347.4 (95% CI 1338.4-1356.3), 4673 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o1 (2024-12-17)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o1 (2024-12-17)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 171 of 416, rating 1347.2 (95% CI 1338.2-1356.2), 4642 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 3 27B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3 27B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 173 of 416, rating 1345.2 (95% CI 1337.5-1352.8), 6303 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Medium 3 (2505)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Medium 3 (2505)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 176 of 416, rating 1343.4 (95% CI 1333.9-1352.8), 4064 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3.5-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3.5-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 177 of 416, rating 1343.1 (95% CI 1336.2-1350.0), 9741 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.5-Air
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.5-Air' (category creative_writing in text/latest-00000-of-00001.parquet): rank 178 of 416, rating 1343.0 (95% CI 1333.6-1352.5), 3995 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Sonnet 4 (20250514)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Sonnet 4 (20250514)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 179 of 416, rating 1342.0 (95% CI 1333.1-1350.9), 4910 votes. Other board entries for this model, not used: 'Claude Sonnet 4 (Thinking 32K, 20250514)' 1344.8 (rank 174). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Hy3 preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Hy3 preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 181 of 416, rating 1340.2 (95% CI 1321.2-1359.1), 1046 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 2.0 Flash (001)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 2.0 Flash (001)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 182 of 416, rating 1339.2 (95% CI 1331.5-1346.9), 6275 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen2.5-Max
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen2.5-Max' (category creative_writing in text/latest-00000-of-00001.parquet): rank 183 of 416, rating 1338.4 (95% CI 1329.9-1347.0), 5012 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Muse Glimmer
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Muse Glimmer' (category creative_writing in text/latest-00000-of-00001.parquet): rank 184 of 416, rating 1338.3 (95% CI 1315.7-1360.9), 734 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude Haiku 5.5 (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude Haiku 5.5 (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 185 of 416, rating 1335.6 (95% CI 1319.1-1352.2), 1437 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 3 Mini (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 3 Mini (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 186 of 416, rating 1334.3 (95% CI 1320.7-1347.9), 1908 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Inkling-Small
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Inkling-Small' (category creative_writing in text/latest-00000-of-00001.parquet): rank 187 of 416, rating 1334.3 (95% CI 1326.2-1342.3), 7686 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-Coder-480B-A35B-Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-Coder-480B-A35B-Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 189 of 416, rating 1332.9 (95% CI 1322.3-1343.6), 3241 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 1.5 Pro (002)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 1.5 Pro (002)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 190 of 416, rating 1332.4 (95% CI 1325.1-1339.8), 8062 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 3 12B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3 12B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 192 of 416, rating 1331.1 (95% CI 1308.0-1354.1), 600 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiniMax-M2.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M2.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 193 of 416, rating 1330.6 (95% CI 1322.8-1338.4), 6668 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 195 of 416, rating 1328.8 (95% CI 1318.8-1338.8), 3623 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5 mini (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5 mini (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 197 of 416, rating 1325.1 (95% CI 1314.9-1335.3), 3522 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Kimi K2 Preview (0711)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Kimi K2 Preview (0711)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 198 of 416, rating 1323.5 (95% CI 1313.1-1333.8), 3413 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Trinity Large Preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Trinity Large Preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 200 of 416, rating 1319.6 (95% CI 1310.5-1328.7), 4767 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Command A (03-2025)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Command A (03-2025)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 201 of 416, rating 1318.9 (95% CI 1311.8-1326.1), 7600 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 2.0 Flash-Lite Preview (02-05)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 2.0 Flash-Lite Preview (02-05)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 202 of 416, rating 1318.7 (95% CI 1309.5-1327.9), 4104 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o1-preview
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o1-preview' (category creative_writing in text/latest-00000-of-00001.parquet): rank 204 of 416, rating 1317.9 (95% CI 1308.0-1327.9), 4508 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Solar Pro 4
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Solar Pro 4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 205 of 416, rating 1317.8 (95% CI 1308.4-1327.1), 5337 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-30B-A3B-Instruct (2507)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-30B-A3B-Instruct (2507)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 206 of 416, rating 1317.0 (95% CI 1306.0-1327.9), 2963 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: NVIDIA-Nemotron-3-Super-120B-A12B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'NVIDIA-Nemotron-3-Super-120B-A12B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 207 of 416, rating 1316.8 (95% CI 1299.3-1334.3), 1120 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude 3.7 Sonnet (20250219)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude 3.7 Sonnet (20250219)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 208 of 416, rating 1316.5 (95% CI 1308.4-1324.5), 5938 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Other board entries for this model, not used: 'Claude 3.7 Sonnet (Thinking 32K, 20250219)' 1331.6 (rank 191). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: INTELLECT-3
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'INTELLECT-3' (category creative_writing in text/latest-00000-of-00001.parquet): rank 210 of 416, rating 1316.0 (95% CI 1295.3-1336.7), 834 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5.4 nano (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5.4 nano (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 211 of 416, rating 1314.2 (95% CI 1307.1-1321.4), 10363 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-Next-80B-A3B-Thinking
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-Next-80B-A3B-Thinking' (category creative_writing in text/latest-00000-of-00001.parquet): rank 212 of 416, rating 1314.1 (95% CI 1299.9-1328.2), 1777 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Trinity Large Thinking
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Trinity Large Thinking' (category creative_writing in text/latest-00000-of-00001.parquet): rank 215 of 416, rating 1308.4 (95% CI 1299.0-1317.7), 4735 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Small 3.2 (2506)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Small 3.2 (2506)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 219 of 416, rating 1304.5 (95% CI 1291.7-1317.2), 2147 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4.1 mini (2025-04-14)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4.1 mini (2025-04-14)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 220 of 416, rating 1299.3 (95% CI 1290.6-1308.0), 5084 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiniMax-M1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 221 of 416, rating 1297.5 (95% CI 1288.4-1306.5), 4503 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-32B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-32B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 222 of 416, rating 1297.0 (95% CI 1274.7-1319.3), 616 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.7-Flash
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.7-Flash' (category creative_writing in text/latest-00000-of-00001.parquet): rank 223 of 416, rating 1296.0 (95% CI 1282.3-1309.6), 1873 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GLM-4.5V
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GLM-4.5V' (category creative_writing in text/latest-00000-of-00001.parquet): rank 224 of 416, rating 1294.9 (95% CI 1272.2-1317.7), 613 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o4-mini (2025-04-16)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o4-mini (2025-04-16)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 225 of 416, rating 1293.7 (95% CI 1285.5-1301.9), 5786 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Amazon Nova 2 Lite
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Amazon Nova 2 Lite' (category creative_writing in text/latest-00000-of-00001.parquet): rank 226 of 416, rating 1292.4 (95% CI 1278.0-1306.8), 1762 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen-Plus (0125)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen-Plus (0125)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 227 of 416, rating 1292.2 (95% CI 1273.9-1310.6), 931 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4o (2024-05-13)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4o (2024-05-13)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 229 of 416, rating 1291.2 (95% CI 1284.1-1298.3), 16599 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mercury 2
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mercury 2' (category creative_writing in text/latest-00000-of-00001.parquet): rank 230 of 416, rating 1288.8 (95% CI 1263.2-1314.3), 547 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.3 Nemotron Super 49B v1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.3 Nemotron Super 49B v1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 231 of 416, rating 1287.8 (95% CI 1260.9-1314.6), 428 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 4.2 30B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 4.2 30B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 232 of 416, rating 1287.6 (95% CI 1262.5-1312.6), 661 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: QwQ-32B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'QwQ-32B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 233 of 416, rating 1287.4 (95% CI 1277.6-1297.2), 3680 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 3n E4B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3n E4B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 235 of 416, rating 1286.9 (95% CI 1275.8-1298.0), 2854 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: MiniMax-M2
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M2' (category creative_writing in text/latest-00000-of-00001.parquet): rank 236 of 416, rating 1286.5 (95% CI 1266.5-1306.6), 895 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 1.5 Flash (002)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 1.5 Flash (002)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 238 of 416, rating 1285.2 (95% CI 1276.3-1294.1), 5017 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 2 (2024-08-13)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 2 (2024-08-13)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 240 of 416, rating 1284.0 (95% CI 1276.6-1291.4), 9339 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Yi Lightning
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Yi Lightning' (category creative_writing in text/latest-00000-of-00001.parquet): rank 242 of 416, rating 1279.8 (95% CI 1269.5-1290.2), 3781 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: gpt-oss-120b
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'gpt-oss-120b' (category creative_writing in text/latest-00000-of-00001.parquet): rank 243 of 416, rating 1274.4 (95% CI 1264.7-1284.1), 3907 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4o (2024-08-06)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4o (2024-08-06)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 244 of 416, rating 1274.3 (95% CI 1265.9-1282.8), 6756 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o3-mini
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o3-mini' (category creative_writing in text/latest-00000-of-00001.parquet): rank 245 of 416, rating 1272.7 (95% CI 1265.7-1279.7), 8160 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Other board entries for this model, not used: 'o3-mini (High)' 1285.6 (rank 237). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 1.5 Pro (001)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 1.5 Pro (001)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 246 of 416, rating 1272.2 (95% CI 1264.1-1280.3), 11797 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen3-30B-A3B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen3-30B-A3B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 247 of 416, rating 1271.1 (95% CI 1260.8-1281.5), 3340 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 3 4B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 3 4B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 248 of 416, rating 1270.2 (95% CI 1248.4-1292.0), 666 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4 Turbo (2024-04-09)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4 Turbo (2024-04-09)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 254 of 416, rating 1268.2 (95% CI 1260.5-1276.0), 14396 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4o mini (2024-07-18)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4o mini (2024-07-18)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 255 of 416, rating 1267.5 (95% CI 1260.6-1274.5), 10486 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Olmo 3.1 32B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Olmo 3.1 32B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 257 of 416, rating 1264.5 (95% CI 1249.8-1279.2), 1726 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Hunyuan Large (2025-02-10)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Hunyuan Large (2025-02-10)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 258 of 416, rating 1264.1 (95% CI 1240.5-1287.7), 568 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-4.1 nano (2025-04-14)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-4.1 nano (2025-04-14)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 263 of 416, rating 1259.8 (95% CI 1241.6-1278.0), 1005 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Olmo 3 32B Think
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Olmo 3 32B Think' (category creative_writing in text/latest-00000-of-00001.parquet): rank 265 of 416, rating 1256.0 (95% CI 1235.4-1276.6), 863 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 4.1 8B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 4.1 8B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 267 of 416, rating 1250.4 (95% CI 1225.7-1275.0), 696 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.3 70B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.3 70B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 268 of 416, rating 1250.2 (95% CI 1243.2-1257.2), 8045 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: GPT-5 nano (High)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'GPT-5 nano (High)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 269 of 416, rating 1249.6 (95% CI 1229.9-1269.3), 910 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 4 Scout 17B 16E Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 4 Scout 17B 16E Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 270 of 416, rating 1248.7 (95% CI 1238.7-1258.7), 3759 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: o1-mini
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'o1-mini' (category creative_writing in text/latest-00000-of-00001.parquet): rank 275 of 416, rating 1244.0 (95% CI 1236.4-1251.6), 7858 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Large 2 (2407)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large 2 (2407)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 276 of 416, rating 1242.6 (95% CI 1234.0-1251.1), 6692 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Large (2411)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large (2411)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 278 of 416, rating 1241.6 (95% CI 1232.6-1250.6), 4439 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Grok 2 mini (2024-08-13)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 2 mini (2024-08-13)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 279 of 416, rating 1241.3 (95% CI 1233.6-1249.0), 7924 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 2 27B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 2 27B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 280 of 416, rating 1240.4 (95% CI 1233.5-1247.2), 11429 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Athene 70B (0725)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Athene 70B (0725)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 282 of 416, rating 1238.1 (95% CI 1226.8-1249.3), 3097 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-V2.5
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-V2.5' (category creative_writing in text/latest-00000-of-00001.parquet): rank 284 of 416, rating 1236.5 (95% CI 1226.1-1247.0), 3450 votes. Other board entries for this model, not used: 'DeepSeek-V2.5 (1210)' 1284.9 (rank 239). Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 4.2 8B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 4.2 8B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 286 of 416, rating 1234.9 (95% CI 1208.0-1261.8), 635 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude 3 Opus (20240229)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude 3 Opus (20240229)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 287 of 416, rating 1234.6 (95% CI 1228.1-1241.1), 28395 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Command R+ (08-2024)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Command R+ (08-2024)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 288 of 416, rating 1234.4 (95% CI 1219.4-1249.4), 1474 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude 3.5 Haiku (20241022)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude 3.5 Haiku (20241022)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 290 of 416, rating 1232.3 (95% CI 1225.9-1238.8), 9835 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.1 70B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.1 70B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 292 of 416, rating 1231.6 (95% CI 1223.9-1239.4), 8250 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 1.5 Flash (001)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 1.5 Flash (001)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 295 of 416, rating 1221.9 (95% CI 1213.5-1230.3), 9031 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen2.5-72B-Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen2.5-72B-Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 296 of 416, rating 1221.0 (95% CI 1212.6-1229.4), 5684 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemini 1.5 Flash-8B (001)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemini 1.5 Flash-8B (001)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 297 of 416, rating 1217.3 (95% CI 1208.4-1226.1), 5031 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Jamba 1.5 Large
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Jamba 1.5 Large' (category creative_writing in text/latest-00000-of-00001.parquet): rank 300 of 416, rating 1211.5 (95% CI 1195.6-1227.4), 1379 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite-4.0-H-Small
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite-4.0-H-Small' (category creative_writing in text/latest-00000-of-00001.parquet): rank 301 of 416, rating 1209.5 (95% CI 1186.4-1232.7), 706 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3 70B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3 70B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 302 of 416, rating 1209.5 (95% CI 1202.0-1217.0), 22753 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 4.2 3B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 4.2 3B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 303 of 416, rating 1207.0 (95% CI 1179.2-1234.8), 637 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 2 9B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 2 9B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 304 of 416, rating 1205.3 (95% CI 1197.9-1212.8), 8340 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: gpt-oss-20b
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'gpt-oss-20b' (category creative_writing in text/latest-00000-of-00001.parquet): rank 307 of 416, rating 1201.0 (95% CI 1183.2-1218.7), 1234 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Aya Expanse 32B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Aya Expanse 32B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 309 of 416, rating 1199.5 (95% CI 1189.6-1209.5), 3853 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Small 24B Instruct (2501)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Small 24B Instruct (2501)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 313 of 416, rating 1194.4 (95% CI 1182.3-1206.5), 2415 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude 3 Sonnet (20240229)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude 3 Sonnet (20240229)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 317 of 416, rating 1185.9 (95% CI 1177.7-1194.2), 15592 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Phi-4
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Phi-4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 318 of 416, rating 1181.3 (95% CI 1171.7-1191.0), 4062 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Ministral 8B (2410)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Ministral 8B (2410)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 321 of 416, rating 1174.5 (95% CI 1153.1-1196.0), 678 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Qwen2.5-Coder-32B-Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Qwen2.5-Coder-32B-Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 322 of 416, rating 1173.7 (95% CI 1154.6-1192.7), 836 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Command R (08-2024)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Command R (08-2024)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 324 of 416, rating 1169.7 (95% CI 1154.3-1185.0), 1421 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Aya Expanse 8B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Aya Expanse 8B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 325 of 416, rating 1167.8 (95% CI 1152.9-1182.7), 1528 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Jamba 1.5 Mini
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Jamba 1.5 Mini' (category creative_writing in text/latest-00000-of-00001.parquet): rank 327 of 416, rating 1164.1 (95% CI 1148.6-1179.7), 1399 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Large (2402)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large (2402)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 328 of 416, rating 1160.8 (95% CI 1151.5-1170.2), 9056 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral Medium
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Medium' (category creative_writing in text/latest-00000-of-00001.parquet): rank 329 of 416, rating 1157.5 (95% CI 1146.7-1168.2), 5549 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Claude 3 Haiku (20240307)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Claude 3 Haiku (20240307)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 330 of 416, rating 1157.1 (95% CI 1149.5-1164.6), 16718 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.1 8B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.1 8B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 331 of 416, rating 1154.1 (95% CI 1145.8-1162.4), 7346 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Command R
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Command R' (category creative_writing in text/latest-00000-of-00001.parquet): rank 332 of 416, rating 1154.1 (95% CI 1144.4-1163.7), 7836 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3 8B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3 8B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 333 of 416, rating 1149.6 (95% CI 1141.5-1157.7), 15365 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: WizardLM 70B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'WizardLM 70B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 334 of 416, rating 1148.9 (95% CI 1132.2-1165.7), 1779 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 2 2B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 2 2B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 336 of 416, rating 1146.5 (95% CI 1138.4-1154.7), 7094 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mixtral 8x22B Instruct v0.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mixtral 8x22B Instruct v0.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 337 of 416, rating 1141.1 (95% CI 1131.9-1150.4), 7447 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Yi 1.5 34B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Yi 1.5 34B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 339 of 416, rating 1134.9 (95% CI 1123.9-1145.9), 3602 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 3.1 8B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 3.1 8B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 343 of 416, rating 1128.6 (95% CI 1102.2-1155.1), 450 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek-Coder-V2
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek-Coder-V2' (category creative_writing in text/latest-00000-of-00001.parquet): rank 348 of 416, rating 1120.0 (95% CI 1106.7-1133.4), 2271 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 3.1 2B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 3.1 2B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 349 of 416, rating 1115.7 (95% CI 1086.9-1144.5), 442 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Zephyr ORPO 141B A35B v0.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Zephyr ORPO 141B A35B v0.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 350 of 416, rating 1112.9 (95% CI 1089.9-1136.0), 635 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mixtral 8x7B Instruct v0.1
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mixtral 8x7B Instruct v0.1' (category creative_writing in text/latest-00000-of-00001.parquet): rank 351 of 416, rating 1108.5 (95% CI 1100.0-1117.1), 11172 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Yi 34B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Yi 34B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 352 of 416, rating 1107.8 (95% CI 1094.1-1121.5), 2379 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Phi-3 Medium 4K Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Phi-3 Medium 4K Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 353 of 416, rating 1106.2 (95% CI 1095.5-1117.0), 3735 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Zephyr 7B Beta
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Zephyr 7B Beta' (category creative_writing in text/latest-00000-of-00001.parquet): rank 357 of 416, rating 1102.1 (95% CI 1086.2-1118.0), 1993 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Starling LM 7B Alpha
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Starling LM 7B Alpha' (category creative_writing in text/latest-00000-of-00001.parquet): rank 359 of 416, rating 1098.9 (95% CI 1083.6-1114.2), 1701 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: OpenHermes 2.5 Mistral 7B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'OpenHermes 2.5 Mistral 7B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 360 of 416, rating 1096.9 (95% CI 1075.4-1118.5), 811 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Starling LM 7B Beta
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Starling LM 7B Beta' (category creative_writing in text/latest-00000-of-00001.parquet): rank 361 of 416, rating 1095.4 (95% CI 1081.1-1109.7), 2376 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.2 3B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.2 3B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 362 of 416, rating 1093.9 (95% CI 1075.1-1112.8), 1070 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: OpenChat 3.5 (0106)
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'OpenChat 3.5 (0106)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 363 of 416, rating 1092.2 (95% CI 1077.4-1107.1), 1858 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Dolphin 2.2.1 Mistral 7B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Dolphin 2.2.1 Mistral 7B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 370 of 416, rating 1085.5 (95% CI 1052.4-1118.6), 291 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Phi-3 Small 8K Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Phi-3 Small 8K Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 372 of 416, rating 1082.6 (95% CI 1069.6-1095.5), 2400 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 2 70B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 2 70B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 375 of 416, rating 1074.6 (95% CI 1064.6-1084.7), 6376 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 3.0 8B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 3.0 8B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 377 of 416, rating 1070.4 (95% CI 1050.0-1090.9), 895 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Zephyr 7B Alpha
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Zephyr 7B Alpha' (category creative_writing in text/latest-00000-of-00001.parquet): rank 378 of 416, rating 1068.5 (95% CI 1038.6-1098.4), 399 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral 7B Instruct v0.2
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral 7B Instruct v0.2' (category creative_writing in text/latest-00000-of-00001.parquet): rank 379 of 416, rating 1067.4 (95% CI 1054.9-1079.9), 2952 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: DeepSeek LLM 67B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'DeepSeek LLM 67B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 380 of 416, rating 1067.2 (95% CI 1045.3-1089.0), 789 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 1.1 7B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 1.1 7B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 381 of 416, rating 1059.2 (95% CI 1047.5-1070.9), 3409 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Vicuna 13B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Vicuna 13B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 382 of 416, rating 1057.9 (95% CI 1045.3-1070.4), 3346 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 2 13B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 2 13B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 383 of 416, rating 1046.6 (95% CI 1034.2-1059.1), 3296 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Granite 3.0 2B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Granite 3.0 2B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 384 of 416, rating 1046.0 (95% CI 1025.3-1066.7), 916 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 2 7B Chat
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 2 7B Chat' (category creative_writing in text/latest-00000-of-00001.parquet): rank 389 of 416, rating 1033.0 (95% CI 1019.4-1046.6), 2341 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Llama 3.2 1B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Llama 3.2 1B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 390 of 416, rating 1032.5 (95% CI 1012.8-1052.3), 1091 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Code Llama 34B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Code Llama 34B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 391 of 416, rating 1031.4 (95% CI 1014.8-1048.0), 1507 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: StripedHyena Nous 7B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'StripedHyena Nous 7B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 393 of 416, rating 1029.0 (95% CI 1008.4-1049.7), 869 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Mistral 7B Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral 7B Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 394 of 416, rating 1028.1 (95% CI 1011.3-1045.0), 1689 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Phi-3 Mini 128K Instruct
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Phi-3 Mini 128K Instruct' (category creative_writing in text/latest-00000-of-00001.parquet): rank 396 of 416, rating 1024.0 (95% CI 1010.0-1037.9), 2949 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 7B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 7B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 397 of 416, rating 1023.3 (95% CI 1005.7-1040.8), 1345 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Vicuna 7B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Vicuna 7B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 398 of 416, rating 1020.8 (95% CI 1003.0-1038.7), 1323 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 1.1 2B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 1.1 2B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 399 of 416, rating 997.7 (95% CI 980.9-1014.6), 1486 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Gemma 2B IT
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Gemma 2B IT' (category creative_writing in text/latest-00000-of-00001.parquet): rank 402 of 416, rating 986.2 (95% CI 963.2-1009.2), 696 votes. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Alpaca 13B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Alpaca 13B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 407 of 416, rating 967.3 (95% CI 945.3-989.4), 954 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: ChatGLM2 6B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'ChatGLM2 6B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 409 of 416, rating 940.9 (95% CI 914.6-967.1), 566 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: ChatGLM 6B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'ChatGLM 6B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 413 of 416, rating 899.8 (95% CI 876.0-923.7), 771 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: StableLM Tuned Alpha 7B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'StableLM Tuned Alpha 7B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 414 of 416, rating 867.6 (95% CI 840.3-895.0), 536 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Configuration: Dolly 2.0 12B
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Dolly 2.0 12B' (category creative_writing in text/latest-00000-of-00001.parquet): rank 415 of 416, rating 863.5 (95% CI 836.5-890.4), 565 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Attribution. Source: LMArena (lmarena.ai), CC BY 4.0
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- The row names the exact model configuration, benchmark version, evaluator, harness, and observation date.
- Cost, token, and step averages are evaluated together with the score for the same configuration.
- You validate the configuration in your own Cursor workload before making a model choice.
Be cautious when
- Rows are collapsed into one score per base model or compared across benchmark versions.
- Small score differences are treated as decisive despite Cursor's variance caveat.
- A qualified row, including Grok 4.5's disclosed training-data advantage, is used as neutral winner evidence.
Related benchmarks
Last reviewed: Oct 27, 2026