Vibeleaderboard
← Benchmark guide

Model results

SciCode

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

SciCode

Source
Artificial Analysis
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Scientific coding evaluation; observed 2026-10-19; result date not supplied

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 Opus 5.5

    anthropic/claude-opus-5-5

    66.9%

    View modelEvidence independent

  2. #2Claude Fable 5.1

    anthropic/claude-fable-5-1

    63.1%

    View modelEvidence independent

  3. #3Gemini 4 Argon

    google/gemini-4-argon-20261013

    61.8%

    View modelEvidence independent

  4. #4Claude Fable 5

    anthropic/claude-fable-5

    61%

    View modelEvidence independent

  5. #4Claude Sonnet 5.5

    anthropic/claude-sonnet-5-5

    61%

    View modelEvidence independent

  6. #6MiMo-V2.6-Pro

    xiaomi/mimo-v2.6-pro-20260921

    60.9%

    View modelEvidence independent

  7. #7Muse Wonder

    meta/muse-wonder-20261012

    60.3%

    View modelEvidence independent

  8. #8Kimi K3

    moonshotai/kimi-k3-20260715

    59.5%

    View modelEvidence independent

  9. #9GLM 5.3

    z-ai/glm-5.3-20260816

    59%

    View modelEvidence independent

  10. #10Step 5 Preview

    stepfun/step-5-preview-20261008

    58.9%

    View modelEvidence independent

  11. #11Muse Spark 1.3

    meta/muse-spark-1.3-20260902

    58.8%

    View modelEvidence independent

  12. #12Muse Spark Open

    meta/muse-spark-open-20261015

    58.4%

    View modelEvidence independent

  13. #13GPT-6 Sol

    openai/gpt-6-sol-20260922

    57.6%

    View modelEvidence independent

  14. #14Grok 4.7

    x-ai/grok-4.7-20260916

    57.4%

    View modelEvidence independent

  15. #14Muse Spark 1.2

    meta/muse-spark-1.2-20260805

    57.4%

    View modelEvidence independent

  16. #16Gemini 3.7 Flash

    google/gemini-3.7-flash-20260813

    57.2%

    View modelEvidence independent

  17. #17GPT-5.6 Sol

    openai/gpt-5.6-sol-20260709

    57.1%

    View modelEvidence independent

  18. #18Gemini 3.8 Flash

    google/gemini-3.8-flash-20260902

    56.6%

    View modelEvidence independent

  19. #19GPT-6 Astra

    openai/gpt-6-astra-20260903

    56.5%

    View modelEvidence independent

  20. #19Grok 4.6

    x-ai/grok-4.6-20260810

    56.5%

    View modelEvidence independent

  21. #21Claude Opus 5

    anthropic/claude-opus-5

    56.4%

    View modelEvidence independent

  22. #22DeepSeek V4.1 Flash 1017

    deepseek/deepseek-v4.1-flash-20261017

    55.9%

    View modelEvidence independent

  23. #23Claude Haiku 5.5

    anthropic/claude-haiku-5-5

    55%

    View modelEvidence independent

  24. #23GPT-5.6 Terra

    openai/gpt-5.6-terra-20260709

    55%

    View modelEvidence independent

  25. #25GPT-6 Luna

    openai/gpt-6-luna-20260922

    54.6%

    View modelEvidence independent

  26. #26GPT-6.1 Sol

    openai/gpt-6.1-sol-20260929

    54.2%

    View modelEvidence independent

  27. #26Mistral Large 4

    mistralai/mistral-large-4-0-20261006

    54.2%

    View modelEvidence independent

  28. #28GPT-5.6 Luna

    openai/gpt-5.6-luna-20260709

    53.6%

    View modelEvidence independent

  29. #29Qwen3.8 Max (0902)

    qwen/qwen3.8-max-20260902

    52.1%

    View modelEvidence independent

  30. #30DeepSeek V4.1 Flash

    deepseek/deepseek-v4.1-flash-20260910

    51.9%

    View modelEvidence independent

  31. #31GLM 5.3 Flash

    z-ai/glm-5.3-flash-20260826

    51.6%

    View modelEvidence independent

  32. #32DeepSeek V4 Pro 0813

    deepseek/deepseek-v4-pro-20260813

    51%

    View modelEvidence independent

  33. #33MiMo-V2.5-Pro

    xiaomi/mimo-v2.5-pro-20260422

    50.6%

    View modelEvidence independent

  34. #34Hy3

    tencent/hy3-20260706

    48.6%

    View modelEvidence independent

  35. #34Hy3 preview

    tencent/hy3-preview-20260421

    48.6%

    View modelEvidence independent

  36. #36Nemotron 3.5 Super VL

    nvidia/nemotron-3.5-super-vl-20261015

    47.8%

    View modelEvidence independent

  37. #37MiniMax M3

    minimax/minimax-m3-20260531

    47.1%

    View modelEvidence independent

  38. #38Inkling

    thinkingmachines/inkling-20260715

    47%

    View modelEvidence independent

  39. #39Qwen3.8 27B

    qwen/qwen3.8-27b-20260814

    46.6%

    View modelEvidence independent

  40. #40MiMo-V2.5

    xiaomi/mimo-v2.5-20260422

    43.9%

    View modelEvidence independent

  41. #41Gemini 3.5 Flash Lite

    google/gemini-3.5-flash-lite-20260721

    41.3%

    View modelEvidence independent

  42. #42Nemotron 3 Ultra

    nvidia/nemotron-3-ultra-550b-a55b-20260604

    40.3%

    View modelEvidence independent

  43. #43Mistral Medium 3

    mistralai/mistral-medium-3

    40.2%

    View modelEvidence independent

  44. #43Mistral Medium 3.1

    mistralai/mistral-medium-3.1

    40.2%

    View modelEvidence independent

  45. #43Mistral Medium 3.5

    mistralai/mistral-medium-3.5-20260430

    40.2%

    View modelEvidence independent

  46. #46Command A

    cohere/command-a-03-2025

    38.5%

    View modelEvidence independent

  47. #46Command A+

    cohere/command-a-plus-05-2026

    38.5%

    View modelEvidence independent

  48. #48gpt-oss-120b

    openai/gpt-oss-120b

    34%

    View modelEvidence independent

  49. #49Nemotron 3.5 Lightning

    nvidia/nemotron-3.5-lightning-20260807

    32.1%

    View modelEvidence independent
SciCode model results | VibeLeaderboard