Models: 10 · Tiers: 26 · Samples: 79 · Invalid: 1
Day highlights
GPT-6.1 Sol
8.80 · max (best)
Model page max
8.80 ± 0.18medium
7.17 ± 0.87low
7.13 ± 0.64GPT-6 Astra
8.79 · max (best)
Model page max
8.79 ± 0.02low
8.19 ± 0.36medium
8.00 ± 0.67Grok 4.7
8.13 · xhigh (best)
Model page xhigh
8.13 ± 0.43medium
6.18 ± 0.51low
5.13 ± 1.14GPT-5.6 Sol
7.70 · medium (best)
Model page medium
7.70 ± 0.50max
7.57 ± 0.83low
6.98 ± 1.07GPT-6 Sol
7.60 · max (best)
Model page max
7.60 ± 0.43medium
6.31 ± 0.35low
4.87 ± 0.65Grok 4.6
7.20 · high (best)
Model page high
7.20 ± 0.82GPT-6 Luna
6.47 · max (best)
Model page max
6.47 ± 1.72low
6.01 ± 1.52medium
5.67 ± 1.22GPT-5.6 Terra
6.43 · medium (best)
Model page medium
6.43 ± 1.14low
6.03 ± 1.44max
5.77 ± 0.36GPT-5.6 Luna
6.17 · max (best)
Model page max
6.17 ± 1.82low
4.64 ± 0.77medium
4.21 ± 0.29Grok 4.5
5.93 · high (best)
Model page