Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Claude Sonnet 4.6 wins overall with a score of 80 vs 22 (58 point difference).Claude Sonnet 4.6 wins 4 out of 4 categories.
Claude Sonnet 4.6
96
GPT-OSS 20B
28.8
Claude Sonnet 4.6
93
GPT-OSS 20B
23
Claude Sonnet 4.6
97.1
GPT-OSS 20B
30
Claude Sonnet 4.6
94
GPT-OSS 20B
28
Claude Sonnet 4.6 scores higher overall with 80 vs 22, a difference of 58 points across all benchmarks.
Claude Sonnet 4.6 leads in knowledge tasks with an average score of 96 vs 28.8.
Claude Sonnet 4.6 leads in coding with an average score of 93 vs 23.
Claude Sonnet 4.6 leads in math with an average score of 97.1 vs 30.
Claude Sonnet 4.6 leads in reasoning with an average score of 94 vs 28.