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

#ModelSettingScoreOverall rank
1GPT-6 AstraHigh35.2#7
2Claude Opus 5Medium33.9#24
3GPT-5.6 SolHigh31.4#33
4Claude Opus 4.8High30.1#62
5Claude Sonnet 5High28#116
6GPT-5.6 TerraHigh27.1#69
7Gemini 3.7 FlashLow27.1#38
8Gemini 3.6 FlashMedium27.1#77
9Kimi K3High26.3#60
10GPT-5.6 LunaLow25#129
11Gemini 3.5 FlashLow17.4#106
12Gemini 3.1 Pro (Preview)High15.7#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.