Vibeleaderboard
← Benchmark guide

Model results

FrontierMath

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.

Reviewed recommendation and limits

Use the relevant tier and private/public split for difficult mathematical reasoning.

Each tier, release and public/private split separately. Imported groups below may use different protocols; this review does not certify each run. Difficulty is specialized; tier, dataset release, tools and grader must match before comparing scores.

Publisher results Epoch benchmarking methods
← All evaluation groups

FrontierMath Tier 4 2025-07-01 · private

Source
Epoch AI Benchmarking Hub
Version
tier-4-2025-07-01-private
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Epoch AI run · task v1 · superseded by FrontierMath Tier 4 v2 · private · result date not supplied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. #1Gemini 3.1 Pro Preview

    google/gemini-3.1-pro-preview-20260219

    16.7%

    View modelEvidence independent

  2. #2Claude Opus 4.6

    anthropic/claude-opus-4-6

    14.6%

    View modelEvidence independent

  3. #2Kimi K2.6

    moonshotai/kimi-k2.6-20260420

    14.6%

    View modelEvidence independent

  4. #4GLM 5.1

    z-ai/glm-5.1-20260406

    12.5%

    View modelEvidence independent

  5. #5Qwen3.6 Plus

    qwen/qwen3.6-plus-04-02

    8.3%

    View modelEvidence independent

  6. #6Claude Opus 4.5

    anthropic/claude-opus-4-5

    4.2%

    View modelEvidence independent

  7. #6Gemini 2.5 Flash

    google/gemini-2.5-flash

    4.2%

    View modelEvidence independent

  8. #6Gemini 2.5 Pro

    google/gemini-2.5-pro

    4.2%

    View modelEvidence independent

  9. #6Gemini 3 Flash Preview

    google/gemini-3-flash-preview-20251217

    4.2%

    View modelEvidence independent

  10. #6Qwen3.6 Max Preview

    qwen/qwen3.6-max-preview-20260420

    4.2%

    View modelEvidence independent

  11. #11Claude Sonnet 4.5

    anthropic/claude-sonnet-4-5

    2.1%

    View modelEvidence independent

  12. #11Gemini 2.5 Pro Preview 06-05

    google/gemini-2.5-pro-preview-06-05

    2.1%

    View modelEvidence independent

  13. #11GLM 4.6

    z-ai/glm-4.6

    2.1%

    View modelEvidence independent

  14. #11GLM 5

    z-ai/glm-5-20260211

    2.1%

    View modelEvidence independent

  15. #15Claude Opus 4

    anthropic/claude-opus-4

    0%

    View modelEvidence independent

  16. #15Claude Sonnet 4

    anthropic/claude-sonnet-4

    0%

    View modelEvidence independent

  17. #15GLM 4.7

    z-ai/glm-4.7-20251222

    0%

    View modelEvidence independent

  18. #15GPT-4.1

    openai/gpt-4.1-2025-04-14

    0%

    View modelEvidence independent

  19. #15Kimi K2 Thinking

    moonshotai/kimi-k2-thinking-20251106

    0%

    View modelEvidence independent

  20. #15Qwen3 235B A22B Thinking 2507

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

    0%

    View modelEvidence independent

  21. #15Qwen3.5-Flash

    qwen/qwen3.5-flash-20260224

    0%

    View modelEvidence independent

  22. #15Qwen3.6 Flash

    qwen/qwen3.6-flash

    0%

    View modelEvidence independent
FrontierMath model results | VibeLeaderboard