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...

RP-Bench - Flaw Hunter — leaderboard

Metric: Flaw Hunter Score. Source: huggingface.co. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.672.1
2DeepSeek V3.268.8
3Claude Sonnet 4.567.1
4GLM-4.765.6
5GPT-4.165.5
6Gemini 2.5 Flash60
7mistral-small-creative59.6
8qwen3.5-flash58.3

Interactive version: theaggregate.ai/benchmark?slug=rp-bench-flaw-hunter · 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.