Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-OSS 120B wins overall with a score of 42 vs 33 (9 point difference).GPT-OSS 120B wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Grok 3 [Beta]
39.8
GPT-OSS 120B
43
Grok 3 [Beta]
34
GPT-OSS 120B
50
Grok 3 [Beta]
41
GPT-OSS 120B
48
Grok 3 [Beta]
39
GPT-OSS 120B scores higher overall with 42 vs 33, a difference of 9 points across all benchmarks.
GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 39.8.
GPT-OSS 120B leads in coding with an average score of 43 vs 34.
GPT-OSS 120B leads in math with an average score of 50 vs 41.
GPT-OSS 120B leads in reasoning with an average score of 48 vs 39.