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...

LiveBench Typos — leaderboard

Metric: Score. Source: livebench.ai. 73 models tracked.

Top models

#ModelScore
1Claude 3 Opus (20240229)68
2Claude 3.5 Sonnet (20240620)66
3GPT-4o (2024-05-13)66
4GPT-4 (0613)64
5Hermes 3 - Llama-3.1 70B62
6Gemini 1.5 Pro (Preview 0801)62
7Gemini 1.5 Pro (Preview 0827)62
8GPT-4o (2024-08-06)60
9Llama 3.1 405B Instruct58
10GPT-4o ChatGPT56
11Gemini 1.5 Pro (0514)56
12Claude 3 Sonnet (20240229)54
13GPT-4 Turbo52
14Mistral Large 2 (Jul)50
15Claude 3 Haiku (20240307)48

Interactive version: theaggregate.ai/benchmark?slug=livebench-typos · 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.