CHI-Bench (Claude Code): leaderboard
Metric: Pass@1 (%). Source: actava.ai. Saturation forecast: Around September 2028. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 37.33 |
| 2 | Claude Opus 4.8 | 33.33 |
| 3 | Claude Opus 4.6 | 28 |
| 4 | Claude Sonnet 4.6 | 26.22 |
| 5 | Claude Opus 4.7 | 24.44 |
| 6 | Claude Fable 5 | 24 |
| 7 | Claude Sonnet 5 | 20 |
| 8 | Claude Haiku 4.5 | 6.22 |
Interactive version: theaggregate.ai/benchmark?slug=chi-bench-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-09.