Open CoT - LSAT Logical Reasoning — leaderboard
Metric: CoT Gain (%). Source: huggingface.co. 132 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Yi 1.5 34B Chat | 24.71 |
| 2 | Command-R+ (08-2024) | 23.73 |
| 3 | Llama 3 70B Instruct | 22.75 |
| 4 | internlm2-chat-20B | 22.35 |
| 5 | Llama 3.1 Nemotron 70B Instruct | 21.96 |
| 6 | Llama 3.1 8B Instruct | 20.78 |
| 7 | DBRX | 20.59 |
| 8 | Llama-3.1-SuperNova-Lite | 20.59 |
| 9 | DeepSeek R1 Distill Qwen 32B | 20.39 |
| 10 | NeuralLLaMa-3-8B-ORPO-v0.3 | 20.2 |
| 11 | Llama 3.1 70B Instruct | 20 |
| 12 | NeuralLLaMa-3-8B-DT-v0.1 | 19.61 |
| 13 | Llama 3 8B Instruct | 19.22 |
| 14 | Qwen 2.5 7B Instruct | 19.22 |
| 15 | Ministral-8B-Instruct-2410 | 18.63 |
Interactive version: theaggregate.ai/benchmark?slug=open-cot-lsat-logical-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.