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
2026-06-25
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. #1Claude Fable 5.1

    anthropic/claude-fable-5-1

    83.8%

    View modelEvidence independent

  2. #2Claude Fable 5

    anthropic/claude-fable-5

    83.4%

    View modelEvidence independent

  3. #3Muse Spark 1.3

    meta/muse-spark-1.3-20260902

    82.4%

    View modelEvidence independent

  4. #4Claude Opus 5.5

    anthropic/claude-opus-5-5

    82.1%

    View modelEvidence independent

  5. #5GPT-6.1 Sol

    openai/gpt-6.1-sol-20260929

    81.8%

    View modelEvidence independent

  6. #6GPT-5.5

    openai/gpt-5.5-20260423

    80.8%

    View modelEvidence independent

  7. #7Claude Opus 5

    anthropic/claude-opus-5

    80.5%

    View modelEvidence independent

  8. #8Gemini 3.7 Flash

    google/gemini-3.7-flash-20260813

    79.9%

    View modelEvidence independent

  9. #9Kimi K3

    moonshotai/kimi-k3-20260715

    79.5%

    View modelEvidence independent

  10. #9Qwen3.8 Max

    qwen/qwen3.8-max-20260803

    79.5%

    View modelEvidence independent

  11. #11Grok 4.6

    x-ai/grok-4.6-20260810

    79%

    View modelEvidence independent

  12. #12Muse Spark 1.2

    meta/muse-spark-1.2-20260805

    78.9%

    View modelEvidence independent

  13. #13GPT-5.4

    openai/gpt-5.4-20260305

    78.8%

    View modelEvidence independent

  14. #14Grok 4.7

    x-ai/grok-4.7-20260916

    78.3%

    View modelEvidence independent

  15. #15Claude Sonnet 5.5

    anthropic/claude-sonnet-5-5

    78.2%

    View modelEvidence independent

  16. #15DeepSeek V4 Pro 0813

    deepseek/deepseek-v4-pro-20260813

    78.2%

    View modelEvidence independent

  17. #17Gemini 3.1 Pro Preview

    google/gemini-3.1-pro-preview-20260219

    78%

    View modelEvidence independent

  18. #17Gemini 3.1 Pro Preview Custom Tools

    google/gemini-3.1-pro-preview-customtools-20260219

    78%

    View modelEvidence independent

  19. #19DeepSeek V4 Flash Vision Exp

    deepseek/deepseek-v4-flash-vision-exp-20260821

    77.7%

    View modelEvidence independent

  20. #20Gemini 3.8 Flash

    google/gemini-3.8-flash-20260902

    77.5%

    View modelEvidence independent

  21. #21Claude Opus 4.8

    anthropic/claude-opus-4-8

    77.1%

    View modelEvidence independent

  22. #21Grok 4.5

    x-ai/grok-4.5-20260708

    77.1%

    View modelEvidence independent

  23. #23Claude Opus 4.7

    anthropic/claude-opus-4-7

    77%

    View modelEvidence independent

  24. #24Claude Sonnet 5

    anthropic/claude-sonnet-5

    76.6%

    View modelEvidence independent

  25. #24GLM 5.3

    z-ai/glm-5.3-20260816

    76.6%

    View modelEvidence independent

  26. #26Muse Spark 1.1

    meta/muse-spark-1.1-20260709

    76%

    View modelEvidence independent

  27. #27Qwen3.8 27B

    qwen/qwen3.8-27b-20260814

    75.8%

    View modelEvidence independent

  28. #28Gemini 3.5 Flash

    google/gemini-3.5-flash-20260519

    75.4%

    View modelEvidence independent

  29. #29Claude Opus 4.6

    anthropic/claude-opus-4-6

    75.1%

    View modelEvidence independent

  30. #30DeepSeek V4 Flash 0731

    deepseek/deepseek-v4-flash-20260731

    74.8%

    View modelEvidence independent

  31. #31Gemini 3.6 Flash

    google/gemini-3.6-flash-20260721

    74.5%

    View modelEvidence independent

  32. #32Qwen3.7 Max

    qwen/qwen3.7-max-20260520

    74.1%

    View modelEvidence independent

  33. #33GPT-5.2-Codex

    openai/gpt-5.2-codex-20260114

    74%

    View modelEvidence independent

  34. #34Claude Sonnet 4.6

    anthropic/claude-sonnet-4-6

    73.4%

    View modelEvidence independent

  35. #34GLM 5.2

    z-ai/glm-5.2-20260616

    73.4%

    View modelEvidence independent

  36. #36Inkling

    thinkingmachines/inkling-20260715

    72.9%

    View modelEvidence independent

  37. #37Mistral Large 4

    mistralai/mistral-large-4-0-20261006

    72.8%

    View modelEvidence independent

  38. #38GLM 5.3 Flash

    z-ai/glm-5.3-flash-20260826

    71.1%

    View modelEvidence independent

  39. #39Kimi K2.6

    moonshotai/kimi-k2.6-20260420

    70.9%

    View modelEvidence independent

  40. #40GPT-5.4 Nano

    openai/gpt-5.4-nano-20260317

    70.8%

    View modelEvidence independent

  41. #41Qwen3.6 Plus

    qwen/qwen3.6-plus-04-02

    69%

    View modelEvidence independent

  42. #42Kimi K2.7 Code

    moonshotai/kimi-k2.7-code-20260612

    68.8%

    View modelEvidence independent

  43. #43Grok Build 0.1

    x-ai/grok-build-0.1-20260520

    68.6%

    View modelEvidence independent

  44. #44Claude Haiku 5.5

    anthropic/claude-haiku-5-5

    68.4%

    View modelEvidence independent

  45. #45MiniMax M3

    minimax/minimax-m3-20260531

    67.5%

    View modelEvidence independent

  46. #46GPT-5.4 Mini

    openai/gpt-5.4-mini-20260317

    66.6%

    View modelEvidence independent

  47. #47Qwen3.6 27B

    qwen/qwen3.6-27b-20260422

    64.2%

    View modelEvidence independent

  48. #48Gemini 3.5 Flash Lite

    google/gemini-3.5-flash-lite-20260721

    63.8%

    View modelEvidence independent

  49. #49Grok 4.3

    x-ai/grok-4.3-20260430

    63.3%

    View modelEvidence independent
LiveBench model results | VibeLeaderboard