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 (system card). Source: anthropic.com. Source: benchmarklist.com. Saturation forecast: Around January 2028. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 58 | #3 |
| 2 | Claude Mythos 5 | 57 | #2 |
| 3 | Claude Mythos 5.1 | 56 | #1 |
| 4 | Claude Mythos Preview | 54 | #4 |
| 5 | Claude Opus 5 | 49 | #12 |
| 6 | Claude Opus 4.8 | 41 | #37 |
| 7 | Claude Opus 4.7 | 38 | #49 |
| 8 | Claude Sonnet 5.5 | 35 | #11 |
| 9 | Claude Sonnet 5 | 23 | #57 |
| 10 | Claude Opus 4.6 | 21 | #63 |
| 11 | Claude Opus 4.5 | 15 | #83 |
| 12 | Claude Sonnet 4.6 | 14 | #90 |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-net-score · How It Works · Data refreshed daily, snapshot 2026-10-20.