Vibeleaderboard
← Benchmark guide

Model results

LiveBench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use LiveBench V2 as a suite-level complement to AA Intelligence Index for a general-purpose shortlist. Start with its Browser Use or Agentic suite for screenshot interaction or persistent app work. Choose Reasoning for ground-truth answer checks.

V1 and V2 2026-10-14 stay separate. V2 equally averages measured suites and uses one run at supported effort. Grading mixes answer checks, tests, application outcomes and rubrics. Imported groups below may use different protocols; this review does not certify each run. Single runs and averages over different measured suites limit overall comparisons. Research uses rubrics and Design uses visual and structural grading; grader validation is not disclosed. V1 contamination claims do not certify V2. Measurement dates are not reported.

Publisher results LiveBench methodology
← All evaluation groups

LiveBench overall

Source
LiveBench
Version
v1
Measurement date
2026-01-08
Metric
% · Higher is better
Evaluation scope
Mean across that public release's task columns

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. #1GPT-5.1-Codex-Max

    openai/gpt-5.1-codex-max-20251204

    74.4%

    View modelEvidence independent

  2. #2GPT-5.3-Codex

    openai/gpt-5.3-codex-20260224

    72%

    View modelEvidence independent

  3. #3GLM 5.1

    z-ai/glm-5.1-20260406

    70.6%

    View modelEvidence independent

  4. #4GPT-5.1-Codex

    openai/gpt-5.1-codex-20251113

    69.3%

    View modelEvidence independent

  5. #5Kimi K2.5

    moonshotai/kimi-k2.5-0127

    69.2%

    View modelEvidence independent

  6. #6GLM 5

    z-ai/glm-5-20260211

    68.7%

    View modelEvidence independent

  7. #7MiniMax M2.7

    minimax/minimax-m2.7-20260318

    65%

    View modelEvidence independent

  8. #8DeepSeek V3.2

    deepseek/deepseek-v3.2-20251201

    63.1%

    View modelEvidence independent

  9. #9Kimi K2 Thinking

    moonshotai/kimi-k2-thinking-20251106

    62.3%

    View modelEvidence independent

  10. #10Gemini 3.1 Flash Lite

    google/gemini-3.1-flash-lite-20260507

    62.1%

    View modelEvidence independent

  11. #10Gemini 3.1 Flash Lite Preview

    google/gemini-3.1-flash-lite-preview-20260303

    62.1%

    View modelEvidence independent

  12. #12GPT-5.1-Codex-Mini

    openai/gpt-5.1-codex-mini-20251113

    60.8%

    View modelEvidence independent

  13. #13Qwen3.6 Flash

    qwen/qwen3.6-flash

    60.5%

    View modelEvidence independent

  14. #14MiniMax M2.5

    minimax/minimax-m2.5-20260211

    60.3%

    View modelEvidence independent

  15. #15DeepSeek V3.2 Exp

    deepseek/deepseek-v3.2-exp

    58.9%

    View modelEvidence independent

  16. #16GLM 4.7

    z-ai/glm-4.7-20251222

    57.3%

    View modelEvidence independent

  17. #17GLM 4.6

    z-ai/glm-4.6

    54.7%

    View modelEvidence independent

  18. #18Gemini 3 Flash Preview

    google/gemini-3-flash-preview-20251217

    54.4%

    View modelEvidence independent

  19. #19Qwen3 235B A22B

    qwen/qwen3-235b-a22b-04-28

    52.9%

    View modelEvidence independent

  20. #19Qwen3 235B A22B Thinking 2507

    qwen/qwen3-235b-a22b-thinking-2507

    52.9%

    View modelEvidence independent

  21. #21GPT-5 Mini

    openai/gpt-5-mini-2025-08-07

    52.4%

    View modelEvidence independent

  22. #22Gemini 2.5 Flash

    google/gemini-2.5-flash

    52.3%

    View modelEvidence independent

  23. #23Qwen3 Next 80B A3B Thinking

    qwen/qwen3-next-80b-a3b-thinking-2509

    51%

    View modelEvidence independent

  24. #24GLM 5V Turbo

    z-ai/glm-5v-turbo-20260401

    48.8%

    View modelEvidence independent

  25. #25Qwen3 235B A22B Instruct 2507

    qwen/qwen3-235b-a22b-07-25

    48%

    View modelEvidence independent

  26. #26Qwen3 Next 80B A3B Instruct

    qwen/qwen3-next-80b-a3b-instruct-2509

    47.4%

    View modelEvidence independent

  27. #27gpt-oss-120b

    openai/gpt-oss-120b

    46.4%

    View modelEvidence independent

  28. #28Qwen3 32B

    qwen/qwen3-32b-04-28

    42.7%

    View modelEvidence independent

  29. #29Gemini 2.5 Flash Lite

    google/gemini-2.5-flash-lite

    41.5%

    View modelEvidence independent

  30. #30GLM 4.6V

    z-ai/glm-4.6-20251208

    38.9%

    View modelEvidence independent

  31. #31Qwen3 30B A3B

    qwen/qwen3-30b-a3b-04-28

    38.8%

    View modelEvidence independent

  32. #31Qwen3 30B A3B Thinking 2507

    qwen/qwen3-30b-a3b-thinking-2507

    38.8%

    View modelEvidence independent

  33. #33GPT-5 Nano

    openai/gpt-5-nano-2025-08-07

    33.7%

    View modelEvidence independent
LiveBench model results | VibeLeaderboard