Skip to content
Spellwright News

Benchmarks

Vending-Bench 2

Vending-Bench 2

Other · higher is better · 1 model
  1. Gemini 4 Carbon$16484*

Every result

  • Gemini 4 Carbon$16484Reported by the model's maker (Andon Labs leaderboard, as cited by Google), Nov 10, 2026

    Google reports a USD 16,484 ending bank balance for Gemini 4 Carbon on Vending-Bench 2, citing Andon Labs' leaderboard.

    Tasks: Final bank balance in US dollars.

    Setting: Google says its results use the Gemini API at the highest thinking setting unless noted; no numeric budget is stated.

    Limits: Provider-reported: Google publishes the result for its own model; it has not been independently reproduced here. Google says this score comes from a third-party leaderboard; that leaderboard was not opened here, so its run date, harness and settings are unverified. Google says the scores are as of October 2026 for the model it calls Gemini 4 Carbon; equivalence to the build now served on every surface is not established. Results under the same benchmark name can be shown together as reported scores, but unmatched settings and missing methods rule out a controlled ranking.

    Google DeepMind · Google DeepMind · Google DeepMind

No published Vending-Bench 2 score checked yet for: Claude Fable 5.2, Claude Mythos 5.2, Gemini 4 Argon, Claude Sonnet 5.5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Gemini 2.5 Pro Experimental (March 2025), Gemini 2.0 Flash (December 2024 experimental), Qwen2.5-7B, Qwen2.5-7B-Instruct, GPT-4o mini (July 2024 release).