Vibeleaderboard
← Benchmark guide

Model results

WeirdML

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.

Official source
← All evaluation groups

WeirdML

Source
WeirdML via Epoch AI
Version
v2
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
effort high · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. GPT-6 Astra

    openai/gpt-6-astra-20260903

    92.9%

    View modelEvidence aggregated

  2. Claude Fable 5.1

    anthropic/claude-fable-5-1

    92.3%

    View modelEvidence aggregated

  3. Claude Opus 5

    anthropic/claude-opus-5

    91.6%

    View modelEvidence aggregated

  4. GPT-5.6 Sol

    openai/gpt-5.6-sol-20260709

    88.8%

    View modelEvidence aggregated

  5. Claude Fable 5

    anthropic/claude-fable-5

    87.8%

    View modelEvidence aggregated

  6. Gemini 3.8 Flash

    google/gemini-3.8-flash-20260902

    84.8%

    View modelEvidence aggregated

  7. GPT-5.5

    openai/gpt-5.5-20260423

    83.9%

    View modelEvidence aggregated

  8. GPT-5.6 Terra

    openai/gpt-5.6-terra-20260709

    78.3%

    View modelEvidence aggregated

  9. Claude Opus 4.6

    anthropic/claude-opus-4-6

    78%

    View modelEvidence aggregated

  10. Claude Opus 4.7

    anthropic/claude-opus-4-7

    76.4%

    View modelEvidence aggregated

  11. Claude Sonnet 5

    anthropic/claude-sonnet-5

    68.8%

    View modelEvidence aggregated

  12. GLM 5.2

    z-ai/glm-5.2-20260616

    67.3%

    View modelEvidence aggregated

  13. Grok 4.6

    x-ai/grok-4.6-20260810

    67.3%

    View modelEvidence aggregated

  14. Gemini 3.5 Flash

    google/gemini-3.5-flash-20260519

    62.6%

    View modelEvidence aggregated

  15. GPT-5.6 Luna

    openai/gpt-5.6-luna-20260709

    60.9%

    View modelEvidence aggregated

  16. GPT-5.1

    openai/gpt-5.1-20251113

    60.8%

    View modelEvidence aggregated

  17. GPT-5

    openai/gpt-5-2025-08-07

    60.7%

    View modelEvidence aggregated

  18. GPT-5 Pro

    openai/gpt-5-pro-2025-10-06

    60.4%

    View modelEvidence aggregated

  19. GPT-5.4 Mini

    openai/gpt-5.4-mini-20260317

    60.3%

    View modelEvidence aggregated

  20. o3 Pro

    openai/o3-pro-2025-06-10

    58.2%

    View modelEvidence aggregated

  21. DeepSeek V4 Flash 0731

    deepseek/deepseek-v4-flash-20260731

    57%

    View modelEvidence aggregated

  22. Gemini 3.6 Flash

    google/gemini-3.6-flash-20260721

    56.1%

    View modelEvidence aggregated

  23. GPT-5 Codex

    openai/gpt-5-codex

    54.5%

    View modelEvidence aggregated

  24. GPT-5 Mini

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

    52.7%

    View modelEvidence aggregated

  25. o4 Mini

    openai/o4-mini-2025-04-16

    52.6%

    View modelEvidence aggregated

  26. o3

    openai/o3-2025-04-16

    52.4%

    View modelEvidence aggregated

  27. GPT-5.4 Nano

    openai/gpt-5.4-nano-20260317

    49.2%

    View modelEvidence aggregated

  28. gpt-oss-120b

    openai/gpt-oss-120b

    48.2%

    View modelEvidence aggregated

  29. DeepSeek V4 Pro 0423

    deepseek/deepseek-v4-pro-20260423

    46.5%

    View modelEvidence aggregated

  30. o1

    openai/o1-2024-12-17

    46.1%

    View modelEvidence aggregated

  31. DeepSeek V4 Flash 0423

    deepseek/deepseek-v4-flash-20260423

    43.8%

    View modelEvidence aggregated

  32. o3 Mini

    openai/o3-mini-2025-01-31

    43.7%

    View modelEvidence aggregated

  33. gpt-oss-20b

    openai/gpt-oss-20b

    40.9%

    View modelEvidence aggregated

  34. Gemini 3.5 Flash Lite

    google/gemini-3.5-flash-lite-20260721

    39%

    View modelEvidence aggregated

  35. GPT-5 Nano

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

    38.1%

    View modelEvidence aggregated

  36. Inkling

    thinkingmachines/inkling-20260715

    32.3%

    View modelEvidence aggregated
WeirdML model results | VibeLeaderboard