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
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. Gemini 3 Flash Preview

    google/gemini-3-flash-preview-20251217

    1367.2 rating

    View modelEvidence aggregated

  2. Claude Opus 4.7

    anthropic/claude-opus-4-7

    1323.05 rating

    View modelEvidence aggregated

  3. GPT-5.2-Codex

    openai/gpt-5.2-codex-20260114

    1299.9 rating

    View modelEvidence aggregated

  4. GPT-5.1-Codex

    openai/gpt-5.1-codex-20251113

    1244.92 rating

    View modelEvidence aggregated

  5. MiMo-V2.6-Flash

    xiaomi/mimo-v2.6-flash-20260921

    1244.2 rating

    View modelEvidence aggregated

  6. GPT-5.1-Codex-Max

    openai/gpt-5.1-codex-max-20251204

    1208.83 rating

    View modelEvidence aggregated

  7. Qwen3.7 Max

    qwen/qwen3.7-max-20260520

    1189.4 rating

    View modelEvidence aggregated

  8. Gemini 3.1 Pro Preview

    google/gemini-3.1-pro-preview-20260219

    1160.6 rating

    View modelEvidence aggregated

  9. MiMo-V2.6-Pro

    xiaomi/mimo-v2.6-pro-20260921

    1158.1 rating

    View modelEvidence aggregated

  10. Grok 4.20

    x-ai/grok-4.20-20260309

    1150.28 rating

    View modelEvidence aggregated

  11. Kimi K2.6

    moonshotai/kimi-k2.6-20260420

    1092.67 rating

    View modelEvidence aggregated

  12. Claude Opus 4.6

    anthropic/claude-opus-4-6

    996.5 rating

    View modelEvidence aggregated

  13. Inkling

    thinkingmachines/inkling-20260715

    946 rating

    View modelEvidence aggregated

  14. Gemma 4 26B A4B

    google/gemma-4-26b-a4b-it-20260403

    927.17 rating

    View modelEvidence aggregated

  15. Gemma 4 31B

    google/gemma-4-31b-it-20260402

    925.5 rating

    View modelEvidence aggregated

  16. MiMo-V2.5-Pro

    xiaomi/mimo-v2.5-pro-20260422

    899.8 rating

    View modelEvidence aggregated

  17. GLM 5.1

    z-ai/glm-5.1-20260406

    887.1 rating

    View modelEvidence aggregated

  18. Kimi K2.7 Code

    moonshotai/kimi-k2.7-code-20260612

    886.23 rating

    View modelEvidence aggregated

  19. Kimi K2.5

    moonshotai/kimi-k2.5-0127

    821.65 rating

    View modelEvidence aggregated

  20. R1 0528

    deepseek/deepseek-r1-0528

    804.12 rating

    View modelEvidence aggregated

  21. Gemini 3.1 Flash Lite

    google/gemini-3.1-flash-lite-20260507

    797.73 rating

    View modelEvidence aggregated

  22. Mercury 2

    inception/mercury-2-20260304

    785.58 rating

    View modelEvidence aggregated

  23. GLM 5

    z-ai/glm-5-20260211

    765.62 rating

    View modelEvidence aggregated

  24. DeepSeek V3.1 Terminus

    deepseek/deepseek-v3.1-terminus

    745.17 rating

    View modelEvidence aggregated

  25. MiMo-V2-Flash

    xiaomi/mimo-v2-flash

    737.95 rating

    View modelEvidence aggregated

  26. Step 3.7 Flash

    stepfun/step-3.7-flash-20260528

    694.12 rating

    View modelEvidence aggregated

  27. Qwen3.6 Plus

    qwen/qwen3.6-plus-04-02

    670.15 rating

    View modelEvidence aggregated

  28. Gemini 2.5 Flash

    google/gemini-2.5-flash

    661.88 rating

    View modelEvidence aggregated

  29. MiniMax M3

    minimax/minimax-m3-20260531

    640.02 rating

    View modelEvidence aggregated

  30. MiniMax M2.1

    minimax/minimax-m2.1

    623.83 rating

    View modelEvidence aggregated

  31. MiniMax M2.5

    minimax/minimax-m2.5-20260211

    618.17 rating

    View modelEvidence aggregated

  32. MiniMax M2.7

    minimax/minimax-m2.7-20260318

    599.25 rating

    View modelEvidence aggregated

  33. Kimi K2 Thinking

    moonshotai/kimi-k2-thinking-20251106

    597.5 rating

    View modelEvidence aggregated

  34. gpt-oss-120b

    openai/gpt-oss-120b

    575.62 rating

    View modelEvidence aggregated

  35. gpt-oss-20b

    openai/gpt-oss-20b

    566.05 rating

    View modelEvidence aggregated

  36. GPT-4.1

    openai/gpt-4.1-2025-04-14

    558.1 rating

    View modelEvidence aggregated

  37. MiMo-V2.5

    xiaomi/mimo-v2.5-20260422

    513.95 rating

    View modelEvidence aggregated

  38. Qwen3 Coder 480B A35B

    qwen/qwen3-coder-480b-a35b-07-25

    461.45 rating

    View modelEvidence aggregated

  39. Qwen3 Coder Plus

    qwen/qwen3-coder-plus

    456.5 rating

    View modelEvidence aggregated

  40. GLM 4.7

    z-ai/glm-4.7-20251222

    399.48 rating

    View modelEvidence aggregated

  41. Qwen3 Max

    qwen/qwen3-max

    370.45 rating

    View modelEvidence aggregated

  42. Qwen3.5-27B

    qwen/qwen3.5-27b-20260224

    349.45 rating

    View modelEvidence aggregated

  43. GLM 4.5

    z-ai/glm-4.5

    344.82 rating

    View modelEvidence aggregated

  44. GLM 4.6

    z-ai/glm-4.6

    340.82 rating

    View modelEvidence aggregated

  45. Qwen3.6 Flash

    qwen/qwen3.6-flash

    326.4 rating

    View modelEvidence aggregated

  46. Kimi K2 0905

    moonshotai/kimi-k2-0905

    267.12 rating

    View modelEvidence aggregated

  47. Qwen3.5-Flash

    qwen/qwen3.5-flash-20260224

    221.8 rating

    View modelEvidence aggregated

  48. Nemotron 3 Super

    nvidia/nemotron-3-super-120b-a12b-20230311

    213.9 rating

    View modelEvidence aggregated

  49. Codestral 2508

    mistralai/codestral-2508

    137.78 rating

    View modelEvidence aggregated
ALE-Bench model results | VibeLeaderboard