Models: 10 · Tiers: 26 · Samples: 78 · Invalid: 0
Day highlights
GPT-6 Astra
8.85 · max (best)
Model page max
8.85 ± 0.19low
8.31 ± 0.31medium
8.20 ± 0.62GPT-6.1 Sol
8.41 · max (best)
Model page max
8.41 ± 0.18low
8.04 ± 0.71medium
7.87 ± 0.54GPT-6 Sol
7.76 · max (best)
Model page max
7.76 ± 0.47medium
6.25 ± 0.61low
5.34 ± 0.70Grok 4.7
7.70 · xhigh (best)
Model page xhigh
7.70 ± 1.07medium
6.67 ± 1.38low
3.79 ± 0.16GPT-5.6 Sol
7.40 · low (best)
Model page low
7.40 ± 1.06max
7.28 ± 0.31medium
6.70 ± 0.78Grok 4.5
6.71 · high (best)
Model page high
6.71 ± 0.16GPT-5.6 Terra
6.57 · max (best)
Model page max
6.57 ± 1.40medium
6.35 ± 1.56low
5.58 ± 1.75Grok 4.6
6.51 · high (best)
Model page high
6.51 ± 1.28GPT-6 Luna
6.45 · max (best)
Model page max
6.45 ± 0.57medium
5.82 ± 1.17low
5.62 ± 1.25GPT-5.6 Luna
5.57 · max (best)
Model page