Skip to content
Yardstick
  1. Benchmarks
  2. Vending-Bench 2

Vending-Bench 2

Run a simulated vending-machine business for a year; the score is the money left in the bank.

Agents & professional workRun by Andon LabsOfficial leaderboard (opens in a new tab)

Top score
$15,515GPT-6 Astra
Median of field
$8,1649 models scored
Data as of
Oct 8, 2026Andon Labs leaderboard and Epoch AI mirror

Standings

Bars share one axis from $0 to $16,000.

  1. Rank 1
    GPT-6 Astra$15,515

    OpenAI · $10 / $50New

  2. Rank 2
    Gemini 4 Argon$13,718

    Google · $2 / $10NewPreview

  3. Rank 3
    Grok 4.7$10,537

    SpaceXAI · $2 / $6New

  4. Rank 4
    Claude Opus 5.5$9,235

    Anthropic · $4 / $20New

  5. Rank 5
    GLM-5.3$8,164

    Z.ai · $1.40 / $4.40NewOpen weights

  6. Rank 6
    Claude Fable 5.1$5,422

    Anthropic · $10 / $50New

  7. Rank 7
    Kimi K3$5,165

    Moonshot AI · $3 / $15Open weights

  8. Rank 8
    Gemini 3.8 Flash$5,094

    Google · $0.75 / $3.75New

  9. Rank 9
    MiniMax M3$2,158

    MiniMax · $0.30 / $1.20Open weights

Not reported for Vending-Bench 2 · 20

  • ·
    Claude Haiku 5.5—Not reported

    Anthropic · $0.10 / $0.50New

  • ·
    Claude Sonnet 5.5—Not reported

    Anthropic · $2 / $10New

  • ·
    DeepSeek-V4-Pro—Not reported

    DeepSeek · $1.32 / $3.96NewOpen weights

  • ·
    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

  • ·
    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

  • ·
    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

  • ·
    Qwen3.8-Max—Not reported

    Alibaba · $2 / $6

What it measures

Long-horizon coherence. The model finds suppliers, negotiates, sets prices and restocks for a simulated year, with some suppliers acting adversarially.

How it is scored

Final bank balance in US dollars, averaged over several runs. There is no ceiling, so the benchmark cannot saturate in the usual sense.

Read it with care

Run-to-run spread is large — often more than a thousand dollars — so small gaps mean little. Lower-ranked rows here come from Epoch AI's mirror of the leaderboard.

Other benchmarks

  • Artificial Analysis Intelligence Index
  • Epoch Capabilities Index
  • LiveBench
  • Terminal-Bench 4.0
  • SWE-Bench Pro (V2 Hard)
  • Arena WebDev
  • GDPval-AA
  • 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