OpenAI's GPT-OSS models benchmarks worse than DeepSeek R1 and Qwen3 235B (xcancel.com) 8 points by pu_pe 1y ago ↗ HN
[–] davely 1y ago ↗ Not entirely unexpected given that these models have 2x - 5x more parameters than the 120b gpt-oss model.It’s impressive their performance gets so close given the size!
1 comment
[ 3.8 ms ] story [ 14.5 ms ] threadIt’s impressive their performance gets so close given the size!