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
SciCode via Epoch AI
Version
Not reported
Measurement date
Not reported
Metric
% · 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. Muse Spark 1.1

    meta/muse-spark-1.1-20260709

    58.8%

    View modelEvidence aggregated

  2. Gemini 3.1 Pro Preview

    google/gemini-3.1-pro-preview-20260219

    58.7%

    View modelEvidence aggregated

  3. Kimi K2.6

    moonshotai/kimi-k2.6-20260420

    53.5%

    View modelEvidence aggregated

  4. MiMo-V2.6-Flash

    xiaomi/mimo-v2.6-flash-20260921

    51.3%

    View modelEvidence aggregated

  5. Grok Build 0.1

    x-ai/grok-build-0.1-20260520

    50.2%

    View modelEvidence aggregated

  6. MiniMax M2.7

    minimax/minimax-m2.7-20260318

    50.1%

    View modelEvidence aggregated

  7. Inkling Small

    thinkingmachines/inkling-small-20260730

    49.7%

    View modelEvidence aggregated

  8. Qwen3.7 Max

    qwen/qwen3.7-max-20260520

    49.5%

    View modelEvidence aggregated

  9. Kimi K2.5

    moonshotai/kimi-k2.5-0127

    49%

    View modelEvidence aggregated

  10. Kimi K2.7 Code

    moonshotai/kimi-k2.7-code-20260612

    47.8%

    View modelEvidence aggregated

  11. Gemini 2.5 Pro

    google/gemini-2.5-pro

    46.3%

    View modelEvidence aggregated

  12. Qwen3.7 Plus

    qwen/qwen3.7-plus-20260602

    46.1%

    View modelEvidence aggregated

  13. Gemma 4 31B

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

    45.5%

    View modelEvidence aggregated

  14. GLM 4.7

    z-ai/glm-4.7-20251222

    45.1%

    View modelEvidence aggregated

  15. GLM 5.1

    z-ai/glm-5.1-20260406

    44.8%

    View modelEvidence aggregated

  16. Gemini 3.1 Flash Lite

    google/gemini-3.1-flash-lite-20260507

    43.4%

    View modelEvidence aggregated

  17. Qwen3 235B A22B Thinking 2507

    qwen/qwen3-235b-a22b-thinking-2507

    41.4%

    View modelEvidence aggregated

  18. Qwen3.6 Plus

    qwen/qwen3.6-plus-04-02

    40.7%

    View modelEvidence aggregated

  19. GPT-4.1 Mini

    openai/gpt-4.1-mini-2025-04-14

    40.4%

    View modelEvidence aggregated

  20. Gemma 4 26B A4B

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

    40%

    View modelEvidence aggregated

  21. Step 3.7 Flash

    stepfun/step-3.7-flash-20260528

    40%

    View modelEvidence aggregated

  22. DeepSeek V3 0324

    deepseek/deepseek-chat-v3-0324

    39%

    View modelEvidence aggregated

  23. Mercury 2

    inception/mercury-2-20260304

    38.7%

    View modelEvidence aggregated

  24. GLM 4.6

    z-ai/glm-4.6

    38.4%

    View modelEvidence aggregated

  25. R1

    deepseek/deepseek-r1

    38.3%

    View modelEvidence aggregated

  26. DeepSeek V3.1 Terminus

    deepseek/deepseek-v3.1-terminus

    38%

    View modelEvidence aggregated

  27. Qwen3.6 35B A3B

    qwen/qwen3.6-35b-a3b-20260415

    36.6%

    View modelEvidence aggregated

  28. Trinity Large Thinking

    arcee-ai/trinity-large-thinking

    36.1%

    View modelEvidence aggregated

  29. Nemotron 3 Super

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

    36%

    View modelEvidence aggregated

  30. DeepSeek V3

    deepseek/deepseek-chat-v3

    35.8%

    View modelEvidence aggregated

  31. Qwen3 32B

    qwen/qwen3-32b-04-28

    35.4%

    View modelEvidence aggregated

  32. Llama 4 Maverick

    meta/llama-4-maverick-17b-128e-instruct

    33.1%

    View modelEvidence aggregated

  33. Qwen3 30B A3B Thinking 2507

    qwen/qwen3-30b-a3b-thinking-2507

    33%

    View modelEvidence aggregated

  34. Qwen3 Coder Next

    qwen/qwen3-coder-next-2025-02-03

    32.3%

    View modelEvidence aggregated

  35. Qwen3 14B

    qwen/qwen3-14b-04-28

    31.6%

    View modelEvidence aggregated

  36. Qwen3.5-9B

    qwen/qwen3.5-9b-20260310

    29.5%

    View modelEvidence aggregated

  37. Llama 3.3 70B Instruct

    meta/llama-3.3-70b-instruct

    26%

    View modelEvidence aggregated

  38. GPT-4.1 Nano

    openai/gpt-4.1-nano-2025-04-14

    25.9%

    View modelEvidence aggregated

  39. MiMo-V2-Flash

    xiaomi/mimo-v2-flash

    25.9%

    View modelEvidence aggregated

  40. Solar Pro 3

    upstage/solar-pro-3

    25.5%

    View modelEvidence aggregated

  41. Gemma 3 27B

    google/gemma-3-27b-it

    23.3%

    View modelEvidence aggregated

  42. Qwen3 8B

    qwen/qwen3-8b-04-28

    22.6%

    View modelEvidence aggregated

  43. Llama 4 Scout

    meta/llama-4-scout-17b-16e-instruct

    17%

    View modelEvidence aggregated

  44. Gemma 3 12B

    google/gemma-3-12b-it

    16.4%

    View modelEvidence aggregated

  45. Llama 3.1 8B Instruct

    meta/llama-3.1-8b-instruct

    13.2%

    View modelEvidence aggregated
SciCode model results | VibeLeaderboard