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...

RPC-Bench — leaderboard

Metric: F1-like (%). Source: rpc-bench.github.io. 14 models tracked.

Top models

#ModelScore
1GPT-568.2
2GPT-5.265.4
3Claude Sonnet 4.564.64
4Gemini 3 Pro61.46
5Gemini 2.5 Pro60.79
6GLM-4.559.24
7Claude Sonnet 458.48
8DeepSeek V3.256.91
9DeepSeek V3.156.31
10GLM-4.753.02

Interactive version: theaggregate.ai/benchmark?slug=rpc-bench · 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.