Vibeleaderboard
← Benchmark guide

Model results

Humanity's Last Exam

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

Humanity's Last Exam

Source
Hugging Face OpenEvals
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Latest published official benchmark result aggregated by OpenEvals · 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. Kimi K2.5

    moonshotai/kimi-k2.5-0127

    50.2%

    View modelEvidence Evidence class unreported

  2. DeepSeek V3.2

    deepseek/deepseek-v3.2-20251201

    40.8%

    View modelEvidence Evidence class unreported

  3. GLM 5

    z-ai/glm-5-20260211

    30.5%

    View modelEvidence Evidence class unreported

  4. Qwen3.5 397B A17B

    qwen/qwen3.5-397b-a17b-20260216

    28.7%

    View modelEvidence Evidence class unreported

  5. Qwen3.5-122B-A10B

    qwen/qwen3.5-122b-a10b-20260224

    25.3%

    View modelEvidence Evidence class unreported

  6. GLM 4.7

    z-ai/glm-4.7-20251222

    24.8%

    View modelEvidence Evidence class unreported

  7. Qwen3.5-27B

    qwen/qwen3.5-27b-20260224

    24.3%

    View modelEvidence Evidence class unreported

  8. Kimi K2 Thinking

    moonshotai/kimi-k2-thinking-20251106

    23.9%

    View modelEvidence Evidence class unreported

  9. Step 3.5 Flash

    stepfun/step-3.5-flash

    23.1%

    View modelEvidence Evidence class unreported

  10. Qwen3.5-35B-A3B

    qwen/qwen3.5-35b-a3b-20260224

    22.4%

    View modelEvidence Evidence class unreported

  11. MiniMax M2.1

    minimax/minimax-m2.1

    22.2%

    View modelEvidence Evidence class unreported

  12. MiniMax M2.5

    minimax/minimax-m2.5-20260211

    19.4%

    View modelEvidence Evidence class unreported

  13. Nemotron 3 Nano 30B A3B

    nvidia/nemotron-3-nano-30b-a3b

    15.5%

    View modelEvidence Evidence class unreported

  14. GLM 4.7 Flash

    z-ai/glm-4.7-flash-20260119

    14.4%

    View modelEvidence Evidence class unreported

  15. MiniMax M2

    minimax/minimax-m2

    12.5%

    View modelEvidence Evidence class unreported

  16. gpt-oss-20b

    openai/gpt-oss-20b

    4.2%

    View modelEvidence Evidence class unreported
Humanity's Last Exam model results | VibeLeaderboard