Vibeleaderboard
← Benchmark guide

Model results

APEX-Agents

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

APEX-Agents

Source
Mercor via Epoch AI
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
effort unspecified · 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. Gemini 4 Argon

    google/gemini-4-argon-20261013

    82.4%

    View modelEvidence aggregated

  2. Claude Fable 5.1

    anthropic/claude-fable-5-1

    68.6%

    View modelEvidence aggregated

  3. Gemini 3.7 Flash

    google/gemini-3.7-flash-20260813

    67.8%

    View modelEvidence aggregated

  4. Grok 4.6

    x-ai/grok-4.6-20260810

    65.3%

    View modelEvidence aggregated

  5. GPT-6 Astra

    openai/gpt-6-astra-20260903

    64.7%

    View modelEvidence aggregated

  6. Gemini 3.8 Flash

    google/gemini-3.8-flash-20260902

    64.3%

    View modelEvidence aggregated

  7. Qwen3.8 Max

    qwen/qwen3.8-max-20260803

    63.3%

    View modelEvidence aggregated

  8. Muse Spark 1.3

    meta/muse-spark-1.3-20260902

    57.8%

    View modelEvidence aggregated

  9. GLM 5.3

    z-ai/glm-5.3-20260816

    56.6%

    View modelEvidence aggregated

  10. Grok 4.5

    x-ai/grok-4.5-20260708

    56.2%

    View modelEvidence aggregated

  11. GPT-5.5

    openai/gpt-5.5-20260423

    55.1%

    View modelEvidence aggregated

  12. Grok 4.7

    x-ai/grok-4.7-20260916

    54.6%

    View modelEvidence aggregated

  13. Claude Sonnet 5

    anthropic/claude-sonnet-5

    54.5%

    View modelEvidence aggregated

  14. GLM 5.3 Flash

    z-ai/glm-5.3-flash-20260826

    52.8%

    View modelEvidence aggregated

  15. GPT-5.4

    openai/gpt-5.4-20260305

    52.4%

    View modelEvidence aggregated

  16. Kimi K3

    moonshotai/kimi-k3-20260715

    50.6%

    View modelEvidence aggregated

  17. DeepSeek V4 Pro 0813

    deepseek/deepseek-v4-pro-20260813

    47.3%

    View modelEvidence aggregated

  18. Gemini 3.6 Flash

    google/gemini-3.6-flash-20260721

    46.9%

    View modelEvidence aggregated

  19. GLM 5.2

    z-ai/glm-5.2-20260616

    45.2%

    View modelEvidence aggregated

  20. GPT-5.6 Luna

    openai/gpt-5.6-luna-20260709

    43%

    View modelEvidence aggregated

  21. DeepSeek V4.1 Flash

    deepseek/deepseek-v4.1-flash-20260910

    39.5%

    View modelEvidence aggregated

  22. Gemini 3.5 Flash

    google/gemini-3.5-flash-20260519

    27.5%

    View modelEvidence aggregated
APEX-Agents model results | VibeLeaderboard