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...

PrepBench — leaderboard

Metric: End-to-End Prep-Code Acc. (self-reported). Source: benchmarklist.com. 10 models tracked.

Top models

#ModelScore
1GPT-5.1 Codex54.9
2Gemini 3 Flash (Preview)53.3
3Claude Sonnet 4.552
4Kimi K2 (Thinking)49.7
5DeepSeek V3.244.8
6GLM-4.741.5
7Qwen 3 235B A22B38.2
8Grok Code Fast 130.1
9GPT-4o16.7

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