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...

SeePhys — leaderboard

Metric: Total Accuracy (%). Source: seephys.github.io. 22 models tracked.

Top models

#ModelScore
1GPT-5 (High)63.2
2Gemini 2.5 Pro54.9
3O4 Mini51.9
4Grok 449
5O145.6
6Doubao-1.5-Pro43.9
7O3 Mini40.3
8GPT-4.135.3
9Claude 3.7 Sonnet34.6
10QVQ-72B-Preview22.5
11GPT-4o21.9

Interactive version: theaggregate.ai/benchmark?slug=seephys · 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.