Comment by dom96
4 hours ago
For what it's worth, it does perform on par with DeepSeek V4 Pro on my adversarial programming language benchmark[1]. I wouldn't think they would benchmax on that.
4 hours ago
For what it's worth, it does perform on par with DeepSeek V4 Pro on my adversarial programming language benchmark[1]. I wouldn't think they would benchmax on that.
We need many more niche, edge-case-y benchmarks like this
what a bizarre benchmark, cool!