Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Open CoT - LogiQA — leaderboard

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

Top models

#ModelScore
1DeepSeek R1 Distill Qwen 14B13.74
2DeepSeek R1 Distill Llama 8B13.26
3DeepSeek R1 Distill Llama 70B12.62
4NeuralLLaMa-3-8B-DT-v0.111.34
5DeepSeek-R1-Distill-Qwen-7B10.38
6NeuralLLaMa-3-8B-ORPO-v0.310.22
7DeepSeek R1 Distill Qwen 32B10.06
8Qwen 2.5 3B Instruct9.42
9Daredevil-8B-abliterated9.42
10Llama 3 70B Instruct9.11
11Phi-3.5-MoE-instruct8.47
12Llama 3 8B Instruct8.15
13internlm2-chat-20B8.15
14Hermes 3 - Llama-3.1 70B7.99
15Configurable-Yi-1.5-9B-Chat7.99

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

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.