Anthropic AI R&D - Novel Compiler Pass Rate: leaderboard
Novel compiler task from Anthropic's internal AI R&D rule-out suite, the bounded task the Opus 5 card still reports as unsaturated: pass rate on complex tests (percent, higher is better; 90% equals 40 hours of human effort). From Table 2.3.5.A of the Claude Opus 5 System Card (July 2026); the Sonnet 5 row is from Table 2.3.3.A of the Sonnet 5 card.
Metric: Pass Rate on Complex Tests (%). Source: www-cdn.anthropic.com. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos 5 | 85.3 | #8 |
| 2 | Claude Opus 5 | 80.91 | #16 |
| 3 | Claude Sonnet 5 | 76.1 | #65 |
| 4 | Claude Opus 4.7 | 70.4 | #51 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=anthropic-ai-r-d-novel-compiler-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.