Models: 10 · Tiers: 26 · Samples: 82 · Invalid: 4

Day highlights

GPT-6.1 Sol

8.83 · max (best)
Model page

GPT-6 Astra

8.75 · max (best)
Model page

GPT-6 Sol

8.18 · max (best)
Model page

low

5.40 ± 0.64
Judge scores vary between passes
Judge scores vary between passes

GPT-5.6 Sol

7.74 · max (best)
Model page

medium

6.91 ± 0.82
Judge scores vary between passes

GPT-6 Luna

7.34 · max (best)
Model page

low

4.88 ± 0.93
Judge scores vary between passes

GPT-5.6 Terra

6.74 · max (best)
Model page

medium

5.99 ± 1.63

Grok 4.6

6.63 · high (best)
Model page

high

6.63 ± 0.56

Grok 4.7

6.60 · xhigh (best)
Model page

Grok 4.5

6.40 · high (best)
Model page

GPT-5.6 Luna

6.16 · max (best)
Model page