Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Metrics
LLM Benchmark Hub
Loading data...

LiveBench Cta — leaderboard

Metric: Score. Source: livebench.ai. 65 models tracked.

Top models

#ModelScore
1GPT-4o (2024-05-13)64
2Claude 3.5 Sonnet (20240620)62
3GPT-4o ChatGPT60
4Llama 3.1 405B Instruct60
5Phi-3.5-MoE-instruct60
6GPT-4o Mini (2024-07-18)58
7GPT-4o (2024-08-06)58
8Claude 3 Opus (20240229)58
9Gemini 1.5 Flash (Preview 0827)58
10Claude 3 Sonnet (20240229)56
11GPT-4 Preview (0125)56
12Gemini 1.5 Pro (Preview 0801)56
13Llama 3 70B Instruct54
14Gemma 2 27B (IT)54
15GPT-4 Turbo54

Interactive version: aibenchmarks.dev/benchmark?slug=livebench-cta · How the rankings work · Data refreshed daily, snapshot 2026-07-09.