Skip to content
Yardstick
  1. Benchmarks
  2. GDPval-AA

GDPval-AA

Real knowledge-work assignments from 44 occupations — reports, spreadsheets, slide decks — judged head to head.

Agents & professional workRun by Artificial AnalysisOfficial leaderboard (opens in a new tab)

Top score
1,866Claude Opus 5.5
Median of field
1,64718 models scored
Data as of
Oct 8, 2026Artificial Analysis GDPval-AA v2.1

Standings

Dots mark each rating on a shared scale from 1,200 to 1,900; ratings have no meaningful zero, so bar lengths would mislead.

  1. Rank 1
    Claude Opus 5.51,866

    Anthropic · $4 / $20New

  2. Rank 2
    Claude Sonnet 5.51,839

    Anthropic · $2 / $10New

  3. Rank 3
    Claude Fable 5.11,756

    Anthropic · $10 / $50New

  4. Rank 4
    Grok 4.71,712

    SpaceXAI · $2 / $6New

  5. Rank 5
    MiMo-V2.6-Pro1,685

    Xiaomi · $0.435 / $0.87NewOpen weights

  6. Rank 6
    Muse Spark 1.31,684

    Meta · $1.25 / $4.25New

  7. Rank 7
    Qwen3.8-Max1,671

    Alibaba · $2 / $6

  8. Rank 8
    GLM-5.31,651

    Z.ai · $1.40 / $4.40NewOpen weights

  9. Rank 9
    GLM-5.3-Flash1,647

    Z.ai · $0.15 / $0.50NewOpen weights

  10. Rank 10
    Gemini 4 Argon1,626

    Google · $2 / $10NewPreview

  11. Rank 11
    Claude Haiku 5.51,620

    Anthropic · $0.10 / $0.50New

  12. Rank 12
    DeepSeek-V4.1-Flash1,600

    DeepSeek · $0.30 / $1.20NewOpen weights

  13. Rank 13
    GPT-6.1 Sol1,575

    OpenAI · $2 / $10New

  14. Rank 14
    GPT-6 Astra1,542

    OpenAI · $10 / $50New

  15. Rank 15
    Gemini 3.8 Flash1,436

    Google · $0.75 / $3.75New

  16. Rank 16
    GPT-6 Luna1,432

    OpenAI · $0.10 / $0.50New

  17. Rank 17
    Mistral Large 41,424

    Mistral AI · $1.36 / $4.18NewPreview

  18. Rank 18
    MiniMax M31,242

    MiniMax · $0.30 / $1.20Open weights

Not reported for GDPval-AA · 11

  • ·
    DeepSeek-V4-Pro—Not reported

    DeepSeek · $1.32 / $3.96NewOpen weights

  • ·
    Gemini 3.1 Pro—Not reported

    Google · $2 / $12Preview

  • ·
    Gemini 3.5 Flash-Lite—Not reported

    Google · $0.30 / $2.50

  • ·
    Gemma 4 31B—Not reported

    Google · Self-hostedOpen weights

  • ·
    Kimi K2.7 Code—Not reported

    Moonshot AI · $0.95 / $4Open weights

  • ·
    Kimi K3—Not reported

    Moonshot AI · $3 / $15Open weights

  • ·
    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

What it measures

Whether a model can produce the actual deliverables of professional work: 220 tasks across 44 occupations and nine industries, drawn from OpenAI's GDPval task set. Models work in an agent loop with a shell and a web browser.

How it is scored

Outputs are compared in blind pairs and the results fitted to an Elo rating, anchored at 1600. Every model runs in the same Artificial Analysis agent harness, which makes this one of the few like-for-like agent tests.

Read it with care

A relative scale: it says who beats whom, not how good the work is in absolute terms. Intervals are around ±20 points.

Other benchmarks

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