DeepSWE Benchmark Results for GPT 5.6
theanonymousone · 3 hours ago
1 comments
theanonymousone · 3 hours ago
1 comments
tomerlir · 3 hours ago
borderline better
theanonymousone · 3 minutes ago
I wouldn't call it borderline. If we take the chart seriously (if), it means for every budget, the best performance is achieved by a 5.6 variant.