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 AMPS Hard — leaderboard

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

Top models

#ModelScore
1Claude 3.5 Sonnet (20240620)49
2GPT-4o ChatGPT48
3Gemini 1.5 Pro (Preview 0827)46
4GPT-4o (2024-05-13)45
5GPT-4o (2024-08-06)43
6DeepSeek Coder V243
7Gemini 1.5 Pro (Preview 0801)43
8GPT-4 Turbo42
9GPT-4o Mini (2024-07-18)41
10DeepSeek V2.540
11Llama 3.1 405B Instruct38
12Claude 3 Opus (20240229)38
13GPT-4 Preview (0125)37
14Llama 3.1 70B Instruct35
15Gemini 1.5 Pro (0514)34

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