SimpleQA Net Score: leaderboard
SimpleQA closed-book factuality results reported by Anthropic as net score: correct responses minus incorrect responses, with abstentions scoring zero.
Metric: Net score (points). Source: anthropic.com. Source: benchmarklist.com. Saturation forecast: Around October 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 0.51 | #4 |
| 2 | Claude Mythos 5 | 0.49 | #2 |
| 3 | Claude Opus 4.7 | 0.28 | #49 |
| 4 | Claude Opus 4.8 | 0.27 | #37 |
| 5 | Claude Opus 4.6 | 0.16 | #63 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=simpleqa-net-score · How It Works · Data refreshed daily, snapshot 2026-10-20.