Open CoT - LSAT Logical Reasoning: leaderboard
The "LSAT Logical Reasoning" 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 | Yi 1.5 34B Chat | 24.71 | #800 |
| 2 | Command-R+ (08-2024) | 23.73 | #821 |
| 3 | Llama 3 70B Instruct | 22.75 | #634 |
| 4 | internlm2-chat-20B | 22.35 | #999 |
| 5 | Llama 3.1 Nemotron 70B Instruct | 21.96 | #554 |
| 6 | Llama 3.1 8B Instruct | 20.78 | #1035 |
| 7 | DBRX | 20.59 | #1045 |
| 8 | Llama-3.1-SuperNova-Lite | 20.59 | #730 |
| 9 | DeepSeek R1 Distill Qwen 32B | 20.39 | #655 |
| 10 | NeuralLLaMa-3-8B-ORPO-v0.3 | 20.2 | #1174 |
| 11 | Llama 3.1 70B Instruct | 20 | #561 |
| 12 | NeuralLLaMa-3-8B-DT-v0.1 | 19.61 | #923 |
| 13 | Qwen 2.5 7B Instruct | 19.22 | #862 |
| 14 | Llama 3 8B Instruct | 19.22 | #1129 |
| 15 | Ministral-8B-Instruct-2410 | 18.63 | #1094 |
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-logical-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.