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...

Epoch AI - Proofbench — leaderboard

Metric: Score. Source: epoch.ai. 43 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol (Max)77
2Claude Fable 5 (Max)77
3GPT-5.6 Terra (xHigh)71
4Claude Opus 4.8 (Max)69
5Claude Sonnet 5 (Max)66
6GPT-5.4 (xHigh)56
7GPT-5.6 Luna (Max)54
8Claude Opus 4.7 (Max)54
9GPT-5.5 (xHigh)50
10Claude Opus 4.6 (Max)50
11Claude Sonnet 4.6 (Max)45
12Muse Spark 1.139
13Claude Opus 4.5 (20251101) (Unknown)36
14GLM-5.2 (Max)35
15Grok 4.5 (High)30

Interactive version: aibenchmarks.dev/benchmark?slug=epoch-ai-proofbench · How the rankings work · Data refreshed daily, snapshot 2026-07-16.