CoopEval - Reputation (Higher-Order): leaderboard
Mean payoff of an LLM agent on CoopEval (2026) under higher-order reputation (random re-matching with the outcomes of the past co-players of co-players visible), 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 higher-order reputation (random re-matching with the action outcomes of co-players' past co-players also visible), 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 June 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 30B A3B 2507 Instruct | 0.315 | #1100 | |
| 2 | GPT-5.2 | Low | 0.281 | #185 |
| 3 | Claude Sonnet 4.5 | Low | 0.273 | #261 |
| 4 | GPT-4o (2024-05-13) | 0.259 | #732 | |
| 5 | Gemini 3 Flash | Medium | 0.146 | #175 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=coopeval-reputation-higher-order · How It Works · Data refreshed daily, snapshot 2026-11-21.