Vibeleaderboard
← Benchmark guide

Model results

AIME

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

AIME 2026

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. Step 3.5 Flash

    stepfun/step-3.5-flash

    96.7%

    View modelEvidence Evidence class unreported

  2. GLM 5

    z-ai/glm-5-20260211

    95.8%

    View modelEvidence Evidence class unreported

  3. Kimi K2.5

    moonshotai/kimi-k2.5-0127

    95.8%

    View modelEvidence Evidence class unreported

  4. DeepSeek V3.2

    deepseek/deepseek-v3.2-20251201

    94.2%

    View modelEvidence Evidence class unreported

  5. Qwen3.5 397B A17B

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

    93.3%

    View modelEvidence Evidence class unreported

  6. Qwen3.5-35B-A3B

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

    93.3%

    View modelEvidence Evidence class unreported

  7. Qwen3.5-9B

    qwen/qwen3.5-9b-20260310

    92.5%

    View modelEvidence Evidence class unreported

  8. Qwen3.5-27B

    qwen/qwen3.5-27b-20260224

    90.8%

    View modelEvidence Evidence class unreported

  9. Qwen3 30B A3B Thinking 2507

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

    87.5%

    View modelEvidence Evidence class unreported
AIME model results | VibeLeaderboard