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 LCB Generation — leaderboard

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

Top models

#ModelScore
1Claude 3.5 Sonnet (20240620)58
2GPT-4 Turbo52
3GPT-4o (2024-05-13)48
4Mistral Large 2 (Jul)48
5GPT-4o (2024-08-06)46
6GPT-4 Preview (0125)46
7Llama 3.1 405B Instruct44
8DeepSeek V2.543
9GPT-4o Mini (2024-07-18)42
10GPT-4o ChatGPT42
11Gemini 1.5 Pro (Preview 0801)42
12Qwen 2 7B Instruct40
13DeepSeek Coder V240
14Gemini 1.5 Flash (Preview 0827)40
15Claude 3 Opus (20240229)38

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