Open CoT - LSAT Logical Reasoning — leaderboard

Metric: CoT Gain (%). Source: huggingface.co. 132 models tracked.

Top models

#ModelScore
1Yi 1.5 34B Chat24.71
2Command-R+ (08-2024)23.73
3Llama 3 70B Instruct22.75
4internlm2-chat-20B22.35
5Llama 3.1 Nemotron 70B Instruct21.96
6Llama 3.1 8B Instruct20.78
7DBRX20.59
8Llama-3.1-SuperNova-Lite20.59
9DeepSeek R1 Distill Qwen 32B20.39
10NeuralLLaMa-3-8B-ORPO-v0.320.2
11Llama 3.1 70B Instruct20
12NeuralLLaMa-3-8B-DT-v0.119.61
13Llama 3 8B Instruct19.22
14Qwen 2.5 7B Instruct19.22
15Ministral-8B-Instruct-241018.63

Interactive version: theaggregate.ai/benchmark?slug=open-cot-lsat-logical-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.