CLASHarness v8 - Mean Score: leaderboard
Metric: Mean check score (%). Source: github.com. Saturation forecast: Around October 2027. 12 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | High | 66.8 | #7 |
| 2 | Claude Opus 5 | High | 64.2 | #24 |
| 3 | GPT-5.6 Sol | High | 63.3 | #33 |
| 4 | Claude Opus 4.8 | High | 62.1 | #62 |
| 5 | Gemini 3.7 Flash | Medium | 61.8 | #38 |
| 6 | GPT-5.6 Luna | High | 60.4 | #129 |
| 7 | GPT-5.6 Terra | High | 60.2 | #69 |
| 8 | Gemini 3.6 Flash | Medium | 60.2 | #77 |
| 9 | Claude Sonnet 5 | High | 59.6 | #116 |
| 10 | Kimi K3 | High | 55.9 | #60 |
| 11 | Gemini 3.1 Pro (Preview) | High | 48.7 | #99 |
| 12 | Gemini 3.5 Flash | Low | 47.3 | #106 |
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-mean-score · How It Works · Data refreshed daily, snapshot 2026-11-18.