Skip to content
Yardstick
  1. Benchmarks
  2. GPQA Diamond

GPQA Diamond

Graduate-level multiple-choice science questions that experts get right and skilled non-experts get wrong.

Knowledge & scienceRun by Epoch AIOfficial leaderboard (opens in a new tab)

Top score
95.8%GPT-6 Astra
Median of field
92.7%14 models scored
Human baseline
69.7%PhD-level domain experts
Data as of
Sep 29, 2026Epoch AI Benchmarking Hub data export

Standings

Bars share one axis from 0% to 100%.

  1. Rank 1
    GPT-6 Astra95.8%

    OpenAI · $10 / $50New

  2. Rank 2
    Claude Sonnet 5.595.6%

    Anthropic · $2 / $10New

  3. Rank 3
    Gemini 3.8 Flash95.4%

    Google · $0.75 / $3.75New

  4. Rank 3
    GPT-6.1 Sol95.4%

    OpenAI · $2 / $10New

  5. Rank 5
    Gemini 3.1 Pro94.4%

    Google · $2 / $12Preview

  6. Rank 6
    Kimi K393.1%

    Moonshot AI · $3 / $15Open weights

  7. Rank 7
    Grok 4.792.7%

    SpaceXAI · $2 / $6New

  8. Rank 8
    Qwen3.8-Max92.7%

    Alibaba · $2 / $6

  9. Rank 9
    DeepSeek-V4-Pro91.7%

    DeepSeek · $1.32 / $3.96NewOpen weights

  10. Rank 10
    GLM-5.390.9%

    Z.ai · $1.40 / $4.40NewOpen weights

  11. Rank 10
    MiniMax M390.9%

    MiniMax · $0.30 / $1.20Open weights

  12. Rank 12
    Claude Opus 5.590.6%

    Anthropic · $4 / $20New

  13. Rank 13
    GPT-6 Luna90.5%

    OpenAI · $0.10 / $0.50New

  14. Rank 14
    GLM-5.3-Flash90.2%

    Z.ai · $0.15 / $0.50NewOpen weights

Not reported for GPQA Diamond · 15

  • ·
    Claude Fable 5.1—Not reported

    Anthropic · $10 / $50New

  • ·
    Claude Haiku 5.5—Not reported

    Anthropic · $0.10 / $0.50New

  • ·
    DeepSeek-V4.1-Flash—Not reported

    DeepSeek · $0.30 / $1.20NewOpen weights

  • ·
    Gemini 3.5 Flash-Lite—Not reported

    Google · $0.30 / $2.50

  • ·
    Gemini 4 Argon—Not reported

    Google · $2 / $10NewPreview

  • ·
    Gemma 4 31B—Not reported

    Google · Self-hostedOpen weights

  • ·
    Kimi K2.7 Code—Not reported

    Moonshot AI · $0.95 / $4Open weights

  • ·
    MiMo-V2.6-Pro—Not reported

    Xiaomi · $0.435 / $0.87NewOpen weights

  • ·
    Mistral Large 4—Not reported

    Mistral AI · $1.36 / $4.18NewPreview

  • ·
    Mistral Medium 3.5—Not reported

    Mistral AI · $1.50 / $7.50Open weights

  • ·
    Mistral Small 4—Not reported

    Mistral AI · $0.15 / $0.60Open weights

  • ·
    Muse Glimmer 30B—Not reported

    Meta · Self-hostedNewOpen weights

  • ·
    Muse Spark 1.3—Not reported

    Meta · $1.25 / $4.25New

  • ·
    Qwen3.8-27B—Not reported

    Alibaba · $0.50 / $3NewOpen weights

  • ·
    Qwen3.8-Flash-Next—Not reported

    Alibaba · $0.15 / $0.47NewOpen weights

What it measures

Graduate-level biology, chemistry and physics, on questions kept because non-experts fail them even with unrestricted web access.

How it is scored

Accuracy on four-option questions, run independently by Epoch AI. Random guessing scores 25%.

Read it with care

Saturated: dozens of models exceed 90% against a 69.7% expert baseline, and the gaps between top models are smaller than the measurement error. Treat it as a floor, not a ranking.

Other benchmarks

  • Artificial Analysis Intelligence Index
  • Epoch Capabilities Index
  • LiveBench
  • Terminal-Bench 4.0
  • SWE-Bench Pro (V2 Hard)
  • Arena WebDev
  • GDPval-AA
  • Vending-Bench 2
  • ARC-AGI-2
  • ARC-AGI-3
  • FrontierMath (Tiers 1–3)
  • MathArena
  • SimpleBench
  • Humanity's Last Exam (Diamond)
  • Arena Vision
  • Arena Text
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs