Vibeleaderboard
← Benchmark guide

Model results

ALE-Bench

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

ALE-Bench

Source
ALE-Bench via Epoch AI
Version
Not reported
Measurement date
Not reported
Metric
rating · 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. Claude Opus 5

    anthropic/claude-opus-5

    2164.57 rating

    View modelEvidence aggregated

  2. Claude Opus 5.5

    anthropic/claude-opus-5-5

    2147.38 rating

    View modelEvidence aggregated

  3. Claude Fable 5.1

    anthropic/claude-fable-5-1

    2143.2 rating

    View modelEvidence aggregated

  4. Claude Fable 5

    anthropic/claude-fable-5

    2041.3 rating

    View modelEvidence aggregated

  5. Claude Sonnet 5.5

    anthropic/claude-sonnet-5-5

    1819.12 rating

    View modelEvidence aggregated

  6. GPT-5.4

    openai/gpt-5.4-20260305

    1607 rating

    View modelEvidence aggregated

  7. Claude Opus 4.8

    anthropic/claude-opus-4-8

    1563.83 rating

    View modelEvidence aggregated

  8. Claude Sonnet 5

    anthropic/claude-sonnet-5

    1463.12 rating

    View modelEvidence aggregated

  9. GLM 5.3

    z-ai/glm-5.3-20260816

    1317.4 rating

    View modelEvidence aggregated

  10. Grok 4.5

    x-ai/grok-4.5-20260708

    1309.28 rating

    View modelEvidence aggregated

  11. GPT-5.2

    openai/gpt-5.2-20251211

    1293.55 rating

    View modelEvidence aggregated

  12. Gemini 3.8 Flash

    google/gemini-3.8-flash-20260902

    1269.72 rating

    View modelEvidence aggregated

  13. GPT-5.1

    openai/gpt-5.1-20251113

    1192.15 rating

    View modelEvidence aggregated

  14. GPT-5.4 Mini

    openai/gpt-5.4-mini-20260317

    1188.58 rating

    View modelEvidence aggregated

  15. GPT-5

    openai/gpt-5-2025-08-07

    1162.45 rating

    View modelEvidence aggregated

  16. GLM 5.2

    z-ai/glm-5.2-20260616

    1046.95 rating

    View modelEvidence aggregated

  17. DeepSeek V4 Pro 0423

    deepseek/deepseek-v4-pro-20260423

    1006.08 rating

    View modelEvidence aggregated

  18. GPT-5.4 Nano

    openai/gpt-5.4-nano-20260317

    1004.52 rating

    View modelEvidence aggregated

  19. o3

    openai/o3-2025-04-16

    933.55 rating

    View modelEvidence aggregated

  20. Gemini 3.5 Flash

    google/gemini-3.5-flash-20260519

    911.02 rating

    View modelEvidence aggregated

  21. Gemini 3.7 Flash

    google/gemini-3.7-flash-20260813

    904.3 rating

    View modelEvidence aggregated

  22. o4 Mini

    openai/o4-mini-2025-04-16

    826.17 rating

    View modelEvidence aggregated

  23. GPT-5 Mini

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

    799.77 rating

    View modelEvidence aggregated

  24. Gemini 3.5 Flash Lite

    google/gemini-3.5-flash-lite-20260721

    765.27 rating

    View modelEvidence aggregated

  25. GPT-5 Nano

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

    718.67 rating

    View modelEvidence aggregated

  26. Gemini 3.6 Flash

    google/gemini-3.6-flash-20260721

    715.52 rating

    View modelEvidence aggregated

  27. DeepSeek V4 Flash 0423

    deepseek/deepseek-v4-flash-20260423

    678.2 rating

    View modelEvidence aggregated

  28. GLM 5.3 Flash

    z-ai/glm-5.3-flash-20260826

    303.55 rating

    View modelEvidence aggregated

  29. Mercury 2.5

    inception/mercury-2.5-20260908

    301.65 rating

    View modelEvidence aggregated
ALE-Bench model results | VibeLeaderboard