Vibeleaderboard
← Benchmark guide

Model results

GPQA Diamond

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 as a compact reference for expert-written science questions, alongside evidence that matches the scientific work you intend to do.

Original GPQA Diamond subset. Preserve prompt, answer extraction, tools, sampling and aggregation. Keep main, extended and third-party corrected subsets separate.. Imported groups below may use different protocols; this review does not certify each run. The static 198-question subset has limited statistical power and exposure risk. Its expert filtering does not make it representative of scientific practice. A Google-proof collection process does not prove present-day contamination resistance.

Publisher results GPQA paper
← All evaluation groups

GPQA Diamond

Source
Epoch AI Benchmarking Hub
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Epoch AI run · task v1 · effort xhigh · 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. #1GPT-5.4 Pro

    openai/gpt-5.4-pro-20260305

    94.6%

    View modelEvidence independent

  2. #2GPT-5.4

    openai/gpt-5.4-20260305

    93.3%

    View modelEvidence independent

  3. #3Grok 4.6

    x-ai/grok-4.6-20260810

    93.2%

    View modelEvidence independent

  4. #4Grok 4.7

    x-ai/grok-4.7-20260916

    92.7%

    View modelEvidence independent

  5. #4Qwen3.8 Max

    qwen/qwen3.8-max-20260803

    92.7%

    View modelEvidence independent

  6. #6Qwen3.8 Max (0902)

    qwen/qwen3.8-max-20260902

    92.3%

    View modelEvidence independent

  7. #7GPT-5.2

    openai/gpt-5.2-20251211

    91.4%

    View modelEvidence independent

  8. #8Claude Sonnet 5

    anthropic/claude-sonnet-5

    90.5%

    View modelEvidence independent

  9. #9Claude Opus 4.7

    anthropic/claude-opus-4-7

    90.2%

    View modelEvidence independent

  10. #10Muse Spark Open

    meta/muse-spark-open-20261015

    88.6%

    View modelEvidence independent

  11. #11Inkling Small

    thinkingmachines/inkling-small-20260730

    88.5%

    View modelEvidence independent

  12. #12Inkling

    thinkingmachines/inkling-20260715

    88.3%

    View modelEvidence independent

  13. #13GPT-5.4 Mini

    openai/gpt-5.4-mini-20260317

    86.9%

    View modelEvidence independent
GPQA Diamond model results | VibeLeaderboard