Models: 10 · Tiers: 26 · Samples: 79 · Invalid: 1

Day highlights

GPT-6.1 Sol

8.83 · max (best)
Model page

GPT-6 Astra

8.72 · max (best)
Model page

GPT-5.6 Luna

7.44 · max (best)
Model page

GPT-5.6 Sol

7.28 · max (best)
Model page

low

6.41 ± 0.51

GPT-6 Sol

7.23 · max (best)
Model page

max

7.23 ± 0.28
Judge scores vary between passes

GPT-6 Luna

6.96 · max (best)
Model page

max

6.96 ± 0.74
Judge scores vary between passes

Grok 4.5

6.54 · high (best)
Model page

Grok 4.7

6.47 · xhigh (best)
Model page

Grok 4.6

6.11 · high (best)
Model page

GPT-5.6 Terra

5.62 · medium (best)
Model page