activeCoding

LiveCodeBench

Metric: Pass@1Introduced: 2024

Continuously updated coding benchmark sourcing new problems from LeetCode, AtCoder, and Codeforces post-May 2023 to eliminate contamination. Evaluates code generation, self-repair, and execution prediction.

Models ranked

79

tracked on this benchmark

Score band

93.5 – 32.8

best → lowest tracked

Snapshot trend

-6.84

Oct 21 → Nov 6 · 1 models

Leaderboard

Tracked models ranked by Pass@1 (higher is better).

Compare candidates
#Model variant and provenanceScore
1
Version: Think Max mode (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
93.5
2

Configuration: Qwen3.8-Omni-Flash

Version: LiveCodeBench v6Harness: Not recordedEvaluator: Qwen (Alibaba)Observed: Oct 26, 2026Confidence: self-reportedSource

Notes: Qwen Team tech report 'Qwen3.8-Omni: Towards Native Omni-Modal Agents' (arXiv 2609.25611v1, 2026-09-22), Table 2 column 'Qwen3.8-Omni-Flash', row 'LiveCodeBench v6': 92.6. Retrieved 2026-10-26.

92.6
3

Configuration: Qwen3.8-Flash

Version: LiveCodeBench v6Harness: Not recordedEvaluator: Qwen (Alibaba)Observed: Oct 26, 2026Confidence: self-reportedSource

Notes: Qwen Team tech report 'Qwen3.8-Omni: Towards Native Omni-Modal Agents' (arXiv 2609.25611v1, 2026-09-22), Table 2 column 'Qwen3.8-Flash', row 'LiveCodeBench v6': 91.9. Identity: the report's 'Qwen3.8-Flash' column and the QwenCloud qwen3.8-flash docs page carry the same values as the Qwen3.8-Flash-Next blog/HF card; Qwen's blog says Qwen3.8-Flash is the production served version (1M context, built-in tools) while these evals used a 256K context. Retrieved 2026-10-26.

91.9
4
Version: Rank 1 on pricepertoken (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
91.7
5
Version: LiveCodeBench pass@1, V4-Flash Think MaxHarness: Not recordedEvaluator: Not recordedObserved: Jul 3, 2026Confidence: Not recordedSource
91.6
6
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
91.6
7
Version: LiveCodeBench; approximate standard GPT-5.5 scoreHarness: Not recordedEvaluator: Not recordedObserved: Apr 24, 2026Confidence: Not recordedSource

Notes: Low-confidence secondary-source row; CodingFleet table marked the GPT-5.5 value as approximate.

91.0
8
Version: LiveCodeBench v6Harness: Not recordedEvaluator: Not recordedObserved: Aug 14, 2026Confidence: Not recordedSource
90.3
9
Version: LiveCodeBench (thinking mode)Harness: Not recordedEvaluator: Not recordedObserved: Oct 13, 2026Confidence: Not recordedSource
90.1
10
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 20, 2026Confidence: Not recordedSource
89.6
11
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Oct 7, 2026Confidence: Not recordedSource
89.0
12
Version: LiveCodeBenchHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource

Notes: Secondary-source competitive-programming row.

88.8
13
Version: LiveCodeBench v6Harness: Not recordedEvaluator: Not recordedObserved: Oct 15, 2026Confidence: Not recordedSource
88.2
14
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
87.8
15
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
87.8
16

Configuration: Solar Pro 4

Version: LiveCodeBench (version not stated), Upstage in-houseHarness: Not recordedEvaluator: UpstageObserved: Oct 26, 2026Confidence: self-reportedSource

Notes: Upstage Solar Pro 4 launch blog (2026-08-11), comparison table (Solar Open 2 / Solar Pro 4 / Gap). Asterisked rows 'evaluated in-house under the same internal evaluation environment'. Row 'LiveCodeBench*': Solar Pro 4 87.8. Retrieved 2026-10-26.

87.8
17
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Jun 2, 2026Confidence: Not recordedSource

Notes: Microsoft AI technical report Table 11 result for MAI-Thinking-1.

87.7
18
Version: 2026-04 (high reasoning mode)Harness: Not recordedEvaluator: Not recordedObserved: Apr 14, 2026Confidence: Not recordedSource
87.3
19
Version: LiveCodeBench v6 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.2
20
Version: Ranked 10th of 120 on LiveCodeBench from DataLearner (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.1
21
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.1
22
Version: LiveCodeBench-V6 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
86.4
23
Version: LiveCodeBench v6Harness: Not recordedEvaluator: Not recordedObserved: Oct 3, 2026Confidence: Not recordedSource

Notes: Aleph Alpha first-party HF model card Aleph-Alpha/Kolibri-1 (FP8 release checkpoint), Evaluation > Post-training table; same value in launch blog/landing page. Harness: Aleph-Alpha-Research eval-framework (Harbor for TerminalBench/SWE-Bench), Kolibri at reasoning effort high, each model at its documented context window. BF16 repo card reports 85.1. Self-reported by the lab.

85.9
24
Version: v6 pass@1, independent Kaggle leaderboardHarness: Not recordedEvaluator: Not recordedObserved: Nov 13, 2025Confidence: Not recordedSource

Notes: independent Kaggle benchmark row; most recent reliable o3 LiveCodeBench figure.

85.5
25
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
85.0
Showing the top 25 of 79 tracked models. Browse all models.

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

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

Related benchmarks

Last reviewed: Apr 15, 2026