LLM Emergent Collusion — leaderboard

Measures the rate at which frontier LLMs spontaneously form price-fixing cartels in a sealed-bid auction simulation — without being instructed to collude. Tests emergent strategic coordination and anti-competitive behavior.

Metric: Collusion Rate (%). Source: github.com. Status: saturated. 13 models tracked.

Top models

#ModelScore
1Grok 475
2O4 Mini62
3Qwen 3 235B A22B57
4O351
5Mistral Medium 347
6Gemini 2.5 Pro39
7Claude Opus 4 (Non-reasoning)36
8Claude Sonnet 4 (Non-reasoning)32
9DeepSeek V3 (0324)26
10GPT-4o (Mar 2025)23
11Grok 319

Interactive version: theaggregate.ai/benchmark?slug=llm-emergent-collusion · How the rankings work · Data refreshed daily, snapshot 2026-07-22.