Models: 10 · Tiers: 26 · Samples: 80 · Invalid: 2

Day highlights

GPT-6.1 Sol

8.74 · max (best)
Model page

GPT-6 Astra

8.67 · max (best)
Model page

GPT-6 Luna

7.83 · max (best)
Model page

max

7.83 ± 0.20
Judge scores vary between passes

low

5.35 ± 0.37
Judge scores vary between passes

medium

5.32 ± 0.38
Judge scores vary between passes

GPT-5.6 Sol

7.67 · max (best)
Model page

medium

7.29 ± 0.70
Judge scores vary between passes
Judge scores vary between passes

low

6.59 ± 0.68

GPT-6 Sol

7.29 · medium (best)
Model page

GPT-5.6 Terra

6.85 · max (best)
Model page

max

6.85 ± 1.45
Judge scores vary between passes

Grok 4.6

6.74 · high (best)
Model page

Grok 4.7

6.65 · medium (best)
Model page

GPT-5.6 Luna

6.30 · max (best)
Model page

medium

5.05 ± 1.25

Grok 4.5

5.80 · high (best)
Model page