CLASHarness v8 - Pass Rate (Easy): leaderboard
Metric: Episode pass rate, easy episodes (%). Source: github.com. Saturation forecast: Around 2029. 12 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | High | 35.2 | #7 |
| 2 | Claude Opus 5 | Medium | 33.9 | #24 |
| 3 | GPT-5.6 Sol | High | 31.4 | #33 |
| 4 | Claude Opus 4.8 | High | 30.1 | #62 |
| 5 | Claude Sonnet 5 | High | 28 | #116 |
| 6 | GPT-5.6 Terra | High | 27.1 | #69 |
| 7 | Gemini 3.7 Flash | Low | 27.1 | #38 |
| 8 | Gemini 3.6 Flash | Medium | 27.1 | #77 |
| 9 | Kimi K3 | High | 26.3 | #60 |
| 10 | GPT-5.6 Luna | Low | 25 | #129 |
| 11 | Gemini 3.5 Flash | Low | 17.4 | #106 |
| 12 | Gemini 3.1 Pro (Preview) | High | 15.7 | #99 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=clasharness-v8-pass-rate-easy · How It Works · Data refreshed daily, snapshot 2026-11-18.