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...

LLM2014 Logic 2025-01 — leaderboard

Metric: Score (%). Source: raw.githubusercontent.com. 29 models tracked.

Top models

#ModelScore
1O191.91
2DeepSeek R184.16
3O1 Mini74.15
4DeepSeek V354.67
5Gemini 2.0 Flash47.59
6MiniMax-Text-0138.04
7Yi Lightning35.47
8Llama 3.1 405B31.93
9Mistral Large 2 (Nov) Instruct (2411)26.84
10GPT-4o Mini21.25

Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2025-01 · 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.