Models: 10 · Tiers: 26 · Samples: 81 · Invalid: 3

Day highlights

GPT-6 Astra

8.77 · max (best)
Model page

GPT-6.1 Sol

8.23 · max (best)
Model page

GPT-5.6 Sol

7.89 · max (best)
Model page

GPT-6 Sol

7.80 · max (best)
Model page

GPT-5.6 Terra

7.54 · max (best)
Model page

max

7.54 ± 0.78
Judge scores vary between passes

low

5.80 ± 1.23

Grok 4.6

7.09 · high (best)
Model page

Grok 4.5

6.93 · high (best)
Model page

GPT-5.6 Luna

6.45 · max (best)
Model page

GPT-6 Luna

6.42 · max (best)
Model page

medium

5.98 ± 0.98
Judge scores vary between passes

low

5.26 ± 0.72

Grok 4.7

6.17 · medium (best)
Model page