ChaosBench-Logic v2 — leaderboard
Metric: MCC (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 60.1 |
| 2 | GPT-5.2 | 50.9 |
| 3 | Qwen 2.5 32B | 47.8 |
| 4 | DeepSeek V3 | 46.9 |
| 5 | Gemini 2.5 Flash | 45.8 |
| 6 | GPT-4o | 45 |
| 7 | Qwen 2.5 14B | 42.6 |
| 8 | Llama 3.3 70B Instruct | 37.3 |
| 9 | Llama 3.1 8B | 24 |
| 10 | Mistral 7B | 22.8 |
Interactive version: theaggregate.ai/benchmark?slug=chaosbench-logic-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.