Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer
How It Works Guesswork Metrics
The Aggregate
Loading data...

Excel-Bench (Humanlaya) — leaderboard

Metric: Average Score (%). Source: humanlaya.com. 6 models tracked.

Top models

#ModelScore
1GPT-5.472.92
2Claude Opus 4.766.01
3Claude Opus 4.665.97
4Kimi K2.544.27

Interactive version: theaggregate.ai/benchmark?slug=excel-bench-humanlaya · How It Works · Data refreshed daily, snapshot 2026-07-27.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.