Skip to content
Yardstick
  1. Benchmarks
  2. SimpleBench

SimpleBench

Everyday trick questions about space, time and people that humans find easy and language models have tended to fumble.

ReasoningRun by SimpleBench teamOfficial leaderboard (opens in a new tab)

Top score
88.4%Claude Opus 5.5
Median of field
81.8%12 models scored
Human baseline
83.7%Average of nine non-specialist people
Data as of
Oct 1, 2026SimpleBench leaderboard

Standings

Bars share one axis from 0% to 100%.

  1. Rank 1
    Claude Opus 5.588.4%

    Anthropic · $4 / $20New

  2. Rank 2
    Claude Fable 5.186.6%

    Anthropic · $10 / $50New

  3. Rank 3
    GPT-6 Astra83.6%

    OpenAI · $10 / $50New

  4. Rank 4
    GPT-6.1 Sol82.9%

    OpenAI · $2 / $10New

  5. Rank 5
    Gemini 3.8 Flash82.4%

    Google · $0.75 / $3.75New

  6. Rank 6
    Muse Spark 1.381.8%

    Meta · $1.25 / $4.25New

  7. Rank 7
    Gemini 3.1 Pro79.6%

    Google · $2 / $12Preview

  8. Rank 8
    Claude Sonnet 5.575.9%

    Anthropic · $2 / $10New

  9. Rank 9
    DeepSeek-V4.1-Flash66.7%

    DeepSeek · $0.30 / $1.20NewOpen weights

  10. Rank 10
    GLM-5.366.2%

    Z.ai · $1.40 / $4.40NewOpen weights

  11. Rank 11
    Kimi K360.7%

    Moonshot AI · $3 / $15Open weights

  12. Rank 12
    MiniMax M345.8%

    MiniMax · $0.30 / $1.20Open weights

Not reported for SimpleBench · 17

  • ·
    Claude Haiku 5.5—Not reported

    Anthropic · $0.10 / $0.50New

  • ·
    DeepSeek-V4-Pro—Not reported

    DeepSeek · $1.32 / $3.96NewOpen 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

  • ·
    GLM-5.3-Flash—Not reported

    Z.ai · $0.15 / $0.50NewOpen weights

  • ·
    GPT-6 Luna—Not reported

    OpenAI · $0.10 / $0.50New

  • ·
    Grok 4.7—Not reported

    SpaceXAI · $2 / $6New

  • ·
    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

  • ·
    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

Common-sense reasoning: spatial and temporal puzzles, social situations and questions with a distracting twist, answerable with ordinary high-school knowledge.

How it is scored

Accuracy on over 200 multiple-choice questions, averaged over five runs.

Read it with care

The best models now beat the 83.7% average of nine non-specialist human testers, so the top of the table has little room left.

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
  • 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