AA-Omniscience Net Score: leaderboard
AA-Omniscience factuality results 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. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Mythos 5 | 58 |
| 2 | Claude Mythos Preview | 54 |
| 3 | Claude Opus 5 | 49 |
| 4 | Claude Opus 4.8 | 41 |
| 5 | Claude Opus 4.7 | 38 |
| 6 | Claude Sonnet 5 | 23 |
| 7 | Claude Opus 4.6 | 21 |
| 8 | Claude Opus 4.5 | 15 |
| 9 | Claude Sonnet 4.6 | 14 |
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-net-score · How It Works · Data refreshed daily, snapshot 2026-09-05.