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 2 — leaderboard

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

Top models

#ModelScore
1DeepSeek R1 Distill Qwen 32B19.02
2DeepSeek R1 Distill Qwen 14B18.7
3DeepSeek R1 Distill Llama 8B18.26
4internlm2-chat-20B17.62
5NeuralLLaMa-3-8B-ORPO-v0.316.48
6Llama 3.1 8B Instruct15.52
7Phi-3.5-MoE-instruct15.14
8Llama 3 70B Instruct15.08
9SOLAR-10.7B-Instruct-v1.015.01
10Daredevil-8B-abliterated15.01
11NeuralLLaMa-3-8B-DT-v0.114.89
12Command-R+ (08-2024)14.76
13openbuddy-yi1.5-9B-v21.1-32k14.69
14DeepSeek R1 Distill Llama 70B14.25
15Llama 3.1 70B Instruct14.19

Interactive version: theaggregate.ai/benchmark?slug=open-cot-logiqa-2 · 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.