Text-to-Video Arena: LMArena Text-to-Video Arena
Crowdsourced human-preference leaderboard for text-to-video models run by LMArena. Voters compare two anonymous clips generated from the same prompt and pick the better one; ratings use a Bradley-Terry model with 95% confidence intervals. Higher is better.
Configurations
10
tracked on this benchmark
Score band
1516.0 – 1065.0
best → lowest tracked
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by Arena Score (higher is better).
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1516 (95% CI 1501-1532), 1,784 votes, rank 1 of 48, category overall, leaderboard published 2026-09-22. Board entry 'gemini-omni-1.1-flash'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1368 (95% CI 1361-1375), 54,167 votes, rank 11 of 48, category overall, leaderboard published 2026-09-22. Board entry 'sora-2-pro'. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: With audio (Gemini API default for this model code: audio always on)
Notes: Arena score 1348 (95% CI 1337-1359), 25,258 votes, rank 16 of 48, category overall, leaderboard published 2026-09-22. Board entry 'veo-3-fast-audio'. Audio entry chosen because Google's Gemini API docs state Veo 3 / Veo 3 Fast audio is always on (https://ai.google.dev/gemini-api/docs/veo). No-audio entry 'veo-3-fast' scored 1248 (kept as alternate). Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1343 (95% CI 1336-1349), 71,947 votes, rank 17 of 48, category overall, leaderboard published 2026-09-22. Board entry 'sora-2'. LLM Reference model is lifecycle-deprecated; score kept as historical. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: With audio (Gemini API default for this model code: audio always on)
Notes: Arena score 1340 (95% CI 1328-1353), 19,002 votes, rank 19 of 48, category overall, leaderboard published 2026-09-22. Board entry 'veo-3-audio'. Audio entry chosen because Google's Gemini API docs state Veo 3 / Veo 3 Fast audio is always on (https://ai.google.dev/gemini-api/docs/veo). No-audio entry 'veo-3' scored 1254 (kept as alternate). Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1256 (95% CI 1249-1263), 76,171 votes, rank 22 of 48, category overall, leaderboard published 2026-09-22. Board entry 'seedance-v1.5-pro'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1206 (95% CI 1184-1228), 1,136 votes, rank 31 of 48, category overall, leaderboard published 2026-09-22. Board entry 'ray-3'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1164 (95% CI 1148-1181), 6,531 votes, rank 39 of 48, category overall, leaderboard published 2026-09-22. Board entry 'veo-2'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1069 (95% CI 1053-1085), 4,082 votes, rank 45 of 48, category overall, leaderboard published 2026-09-22. Board entry 'sora'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Configuration: Overall leaderboard entry (unqualified board entry)
Notes: Arena score 1065 (95% CI 1048-1083), 5,250 votes, rank 46 of 48, category overall, leaderboard published 2026-09-22. Board entry 'ray2'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17.
Attribution. Source: LMArena (lmarena.ai), CC BY 4.0
Scores rounded; model entries mapped to LLM Reference models; snapshot 2026-09-22.
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 17, 2026