Skip to content
Yardstick
  1. Benchmarks
  2. Humanity's Last Exam (Diamond)

Humanity's Last Exam (Diamond)

A thousand expert-written questions at the edge of academic knowledge, across more than a hundred subjects.

Knowledge & scienceRun by Scale AI and the Center for AI SafetyOfficial leaderboard (opens in a new tab)

Top score
60.6%GPT-6 Astra
Median of field
25.4%9 models scored
Data as of
Sep 9, 2026Scale AI Labs leaderboard

Standings

Bars share one axis from 0% to 100%.

  1. Rank 1
    GPT-6 Astra60.6%

    OpenAI · $10 / $50New

  2. Rank 2
    Claude Opus 5.555%

    Anthropic · $4 / $20New

  3. Rank 3
    Claude Fable 5.151.3%

    Anthropic · $10 / $50New

  4. Rank 4
    Gemini 3.8 Flash34.3%

    Google · $0.75 / $3.75New

  5. Rank 5
    Muse Spark 1.325.4%

    Meta · $1.25 / $4.25New

  6. Rank 6
    Grok 4.723.4%

    SpaceXAI · $2 / $6New

  7. Rank 7
    Kimi K322.2%

    Moonshot AI · $3 / $15Open weights

  8. Rank 8
    GLM-5.316.4%

    Z.ai · $1.40 / $4.40NewOpen weights

  9. Rank 9
    DeepSeek-V4-Pro13.4%

    DeepSeek · $1.32 / $3.96NewOpen weights

Not reported for Humanity's Last Exam (Diamond) · 20

  • ·
    Claude Haiku 5.5—Not reported

    Anthropic · $0.10 / $0.50New

  • ·
    Claude Sonnet 5.5—Not reported

    Anthropic · $2 / $10New

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

    DeepSeek · $0.30 / $1.20NewOpen weights

  • ·
    Gemini 3.1 Pro—Not reported

    Google · $2 / $12Preview

  • ·
    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

  • ·
    GLM-5.3-Flash—Not reported

    Z.ai · $0.15 / $0.50NewOpen weights

  • ·
    GPT-6 Luna—Not reported

    OpenAI · $0.10 / $0.50New

  • ·
    GPT-6.1 Sol—Not reported

    OpenAI · $2 / $10New

  • ·
    Kimi K2.7 Code—Not reported

    Moonshot AI · $0.95 / $4Open weights

  • ·
    MiMo-V2.6-Pro—Not reported

    Xiaomi · $0.435 / $0.87NewOpen weights

  • ·
    MiniMax M3—Not reported

    MiniMax · $0.30 / $1.20Open 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

  • ·
    Qwen3.8-27B—Not reported

    Alibaba · $0.50 / $3NewOpen weights

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

    Alibaba · $0.15 / $0.47NewOpen weights

  • ·
    Qwen3.8-Max—Not reported

    Alibaba · $2 / $6

What it measures

Closed-ended expert knowledge and reasoning, from classics to particle physics. Models also state a confidence, so calibration is measured alongside accuracy.

How it is scored

Accuracy on HLE-Diamond, the cleaned 1,000-question subset of Humanity's Last Exam maintained by Scale AI and the Center for AI Safety.

Read it with care

Far from solved: the best score is about 61%. The original 2,500-question set now carries a contamination warning for most models, because its questions were public before those models were tested.

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
  • GPQA 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