Economic Agent Evaluation
Economic Agent Leaderboards
Can an agent negotiate? Can it run a business? And how much money does it lose when the other side plays dirty? We curate the benchmarks that answer these questions, and build the ones that don't exist yet.
Benchmarks
4
Models
26
Last measured
2026-09-11
Benchmarks
Full leaderboards, one page per benchmark.
- ZeroSum-Bench12 models · 2026-08-06leadsGemini 3.1 Pro59.4%→How much money can an agent take from its counterparties?worstZbest
- Treasury-Bench14 models · 2026-09-11leadsGLM-5.3$432→Can the agent manage cash it must never run out of?worstZbest
- TERMS-Bench12 models · 2026-08-04leadsClaude Opus 4.669.4%→Can the agent negotiate well?worstZbest
- Vending-Bench 210 models · 2026-08-04leadsClaude Opus 5$11,182→Can the agent run a business over a long horizon?worstZbest