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 (system card). Source: anthropic.com. Source: benchmarklist.com. Saturation forecast: Around August 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos 5 | 42 | #2 |
| 2 | Claude Mythos Preview | 34 | #4 |
| 3 | Claude Opus 4.7 | 24 | #49 |
| 4 | Claude Sonnet 4.6 | 20 | #90 |
| 5 | Claude Opus 4.8 | 20 | #37 |
| 6 | Claude Opus 4.6 | 19 | #63 |
| 7 | Claude Opus 4.5 | 8 | #83 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=100q-hard-net-score · How It Works · Data refreshed daily, snapshot 2026-10-20.