Multilingual Factual Questions Net Score — leaderboard

Closed-book multilingual 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: saturation imminent. 7 models tracked.

Top models

#ModelScore
1Claude Mythos Preview48
2Claude Mythos 546
3Claude Opus 4.839
4Claude Opus 4.738
5Claude Opus 4.634
6Claude Sonnet 4.630
7Claude Opus 4.528

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