Open CoT - LSAT Reading Comprehension: leaderboard
The "LSAT Reading Comprehension" subtask of Open CoT. A task from the Open CoT Leaderboard, measuring chain-of-thought reasoning ability and the accuracy gain from step-by-step reasoning.
Metric: CoT Gain (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 132 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 8B Instruct | 27.51 | #1035 |
| 2 | Llama 3 8B Instruct | 25.65 | #1129 |
| 3 | aya-expanse-32B | 24.54 | #692 |
| 4 | internlm2-chat-20B | 24.16 | #999 |
| 5 | Llama 3.1 70B Instruct | 23.42 | #561 |
| 6 | Daredevil-8B-abliterated | 23.42 | #846 |
| 7 | Ministral-8B-Instruct-2410 | 23.05 | #1094 |
| 8 | DeepSeek R1 Distill Llama 8B | 22.68 | #1291 |
| 9 | SOLAR-10.7B-Instruct-v1.0 | 22.3 | #1075 |
| 10 | internlm2-chat-7B | 21.56 | #1121 |
| 11 | DeepSeek R1 Distill Qwen 14B | 21.19 | #844 |
| 12 | DBRX | 21.19 | #1045 |
| 13 | Llama 3 70B Instruct | 20.82 | #634 |
| 14 | DeepSeek-R1-Distill-Qwen-7B | 20.82 | #1415 |
| 15 | Yi 1.5 34B Chat | 20.45 | #800 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-cot-lsat-reading-comprehension · How It Works · Data refreshed daily, snapshot 2026-10-20.