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

#ModelSettingScoreOverall rank
1GPT-6 AstraHigh66.8#7
2Claude Opus 5High64.2#24
3GPT-5.6 SolHigh63.3#33
4Claude Opus 4.8High62.1#62
5Gemini 3.7 FlashMedium61.8#38
6GPT-5.6 LunaHigh60.4#129
7GPT-5.6 TerraHigh60.2#69
8Gemini 3.6 FlashMedium60.2#77
9Claude Sonnet 5High59.6#116
10Kimi K3High55.9#60
11Gemini 3.1 Pro (Preview)High48.7#99
12Gemini 3.5 FlashLow47.3#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.