Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek V3.1 (Reasoning) wins overall with a score of 25 vs 22 (3 point difference).DeepSeek V3.1 (Reasoning) wins 4 out of 4 categories.
DeepSeek V3.1 (Reasoning)
31.8
GPT-OSS 20B
28.8
DeepSeek V3.1 (Reasoning)
26
GPT-OSS 20B
23
DeepSeek V3.1 (Reasoning)
33
GPT-OSS 20B
30
DeepSeek V3.1 (Reasoning)
31
GPT-OSS 20B
28
DeepSeek V3.1 (Reasoning) scores higher overall with 25 vs 22, a difference of 3 points across all benchmarks.
DeepSeek V3.1 (Reasoning) leads in knowledge tasks with an average score of 31.8 vs 28.8.
DeepSeek V3.1 (Reasoning) leads in coding with an average score of 26 vs 23.
DeepSeek V3.1 (Reasoning) leads in math with an average score of 33 vs 30.
DeepSeek V3.1 (Reasoning) leads in reasoning with an average score of 31 vs 28.