CoopEval - Mediation: leaderboard
Mean payoff of an LLM agent on CoopEval (2026) under mediation (agents propose public mediators, vote for one and may delegate their action to it), averaged over Prisoners Dilemma, Public Goods, Travelers Dilemma and Trust Game against a population of the other tested LLM agents, each told to maximize its own points. Normalized payoff where 0 is mutual defection and 1 is full cooperation (open scale: below 0 when exploited, above 1 with side payments); higher is better.
Metric: Normalized mean payoff (open scale; below 0 when exploited, above 1 possible under side payments) under mediation (agents propose public mediators, approve one by vote and may delegate their action to it), aggregated over four social dilemmas (Prisoner's Dilemma, Public Goods, Traveler's Dilemma, Trust Game) after shifting and rescaling payoffs so that 0 is everyone defecting and 1 is everyone playing the most cooperative action; the model's mean payoff across all cross-play match-ups with the six tested LLM agents (a uniform population), each instructed to maximize its own points, temperature 1, three repeats per combination; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Flash | Medium | 0.868 | #175 |
| 2 | Claude Sonnet 4.5 | Low | 0.863 | #261 |
| 3 | GPT-5.2 | Low | 0.76 | #185 |
| 4 | Qwen 3 30B A3B 2507 Instruct | 0.583 | #1100 | |
| 5 | GPT-4o (2024-05-13) | 0.243 | #732 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=coopeval-mediation · How It Works · Data refreshed daily, snapshot 2026-11-21.