Models: 10 · Tiers: 26 · Samples: 82 · Invalid: 4
Day highlights
GPT-6.1 Sol
8.83 · max (best)
Model page max
8.83 ± 0.15medium
7.88 ± 0.61low
7.79 ± 0.18GPT-6 Astra
8.75 · max (best)
Model page max
8.75 ± 0.22low
8.48 ± 0.27medium
8.36 ± 0.37GPT-6 Sol
8.18 · max (best)
Model page max
8.18 ± 0.04medium
6.61 ± 0.72low
5.40 ± 0.64GPT-5.6 Sol
7.74 · max (best)
Model page max
7.74 ± 1.00medium
6.91 ± 0.82low
5.40 ± 0.66GPT-6 Luna
7.34 · max (best)
Model page max
7.34 ± 1.44medium
5.77 ± 1.66low
4.88 ± 0.93GPT-5.6 Terra
6.74 · max (best)
Model page max
6.74 ± 1.66medium
5.99 ± 1.63low
5.95 ± 1.38Grok 4.6
6.63 · high (best)
Model page high
6.63 ± 0.56Grok 4.7
6.60 · xhigh (best)
Model page xhigh
6.60 ± 0.77medium
5.56 ± 0.51low
5.55 ± 0.58Grok 4.5
6.40 · high (best)
Model page high
6.40 ± 0.52GPT-5.6 Luna
6.16 · max (best)
Model page