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

Day highlights

GPT-6 Astra

8.88 · max (best)
Model page

GPT-6.1 Sol

8.88 · max (best)
Model page

low

7.90 ± 0.64
Judge scores vary between passes

medium

7.74 ± 1.04
Judge scores vary between passes

GPT-5.6 Sol

8.23 · max (best)
Model page

GPT-6 Sol

7.99 · max (best)
Model page

GPT-5.6 Terra

7.04 · low (best)
Model page

low

7.04 ± 0.88

Grok 4.6

7.02 · high (best)
Model page

GPT-6 Luna

6.87 · medium (best)
Model page

medium

6.87 ± 1.13
Judge scores vary between passes

low

6.29 ± 1.38

Grok 4.5

6.63 · high (best)
Model page

GPT-5.6 Luna

6.62 · max (best)
Model page

medium

4.71 ± 0.72

Grok 4.7

6.15 · xhigh (best)
Model page