100Q-Hard Net Score — leaderboard

Closed-book factuality benchmark reported by Anthropic as net score: correct responses minus incorrect responses, with abstentions scoring zero.

Metric: Net score (self-reported). Source: benchmarklist.com. Status: years away from saturation. 7 models tracked.

Top models

#ModelScore
1Claude Mythos 542
2Claude Mythos Preview34
3Claude Opus 4.724
4Claude Sonnet 4.620
5Claude Opus 4.820
6Claude Opus 4.619
7Claude Opus 4.58

Interactive version: theaggregate.ai/benchmark?slug=100q-hard-net-score · How the rankings work · Data refreshed daily, snapshot 2026-07-22.