CLASHarness v8 - All Pass: leaderboard

Metric: Episode pass rate (%). Source: github.com. Saturation forecast: Around 2029. 12 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraHigh28.7#7
2Claude Opus 5Medium25.3#24
3GPT-5.6 SolHigh24.5#33
4Claude Opus 4.8Medium23.8#62
5Kimi K3High21.8#60
6Gemini 3.7 FlashMedium21.5#38
7Claude Sonnet 5High20.8#116
8Gemini 3.6 FlashMedium20.2#77
9GPT-5.6 TerraHigh20#69
10GPT-5.6 LunaHigh19.8#129
11Gemini 3.5 FlashLow13.5#106
12Gemini 3.1 Pro (Preview)High12#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-all-pass · How It Works · Data refreshed daily, snapshot 2026-11-18.