benchlm.ai

GPT-OSS 20B vs Qwen3 235B 2507 (Reasoning)

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Qwen3 235B 2507 (Reasoning) wins overall with a score of 31 vs 22 (9 point difference).Qwen3 235B 2507 (Reasoning) wins 4 out of 4 categories.

GPT-OSS 20B

CreatorOpenAI
TypeOpen Weight
Context128K
Score22

Qwen3 235B 2507 (Reasoning)

CreatorAlibaba
TypeOpen Weight
Context128K
Score31

Knowledge

Qwen3 235B 2507 (Reasoning)

GPT-OSS 20B

28.8

Qwen3 235B 2507 (Reasoning)

37.8

31
MMLU
40
30
GPQA
39
28
SuperGPQA
37
26
OpenBookQA
35

Coding

Qwen3 235B 2507 (Reasoning)

GPT-OSS 20B

23

Qwen3 235B 2507 (Reasoning)

32

23
HumanEval
32

Mathematics

Qwen3 235B 2507 (Reasoning)

GPT-OSS 20B

30

Qwen3 235B 2507 (Reasoning)

39

31
AIME 2023
40
33
AIME 2024
42
32
AIME 2025
41
27
HMMT Feb 2023
36
29
HMMT Feb 2024
38
28
HMMT Feb 2025
37
30
BRUMO 2025
39

Reasoning

Qwen3 235B 2507 (Reasoning)

GPT-OSS 20B

28

Qwen3 235B 2507 (Reasoning)

37

29
SimpleQA
38
27
MuSR
36

Frequently Asked Questions

Which is better, GPT-OSS 20B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) scores higher overall with 31 vs 22, a difference of 9 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 20B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) leads in knowledge tasks with an average score of 37.8 vs 28.8.

Which is better for coding, GPT-OSS 20B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) leads in coding with an average score of 32 vs 23.

Which is better for math, GPT-OSS 20B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) leads in math with an average score of 39 vs 30.

Which is better for reasoning, GPT-OSS 20B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) leads in reasoning with an average score of 37 vs 28.

Related Comparisons

GPT-OSS 20B vs GPT-5.4GPT-OSS 20B vs Gemini 3.1 ProGPT-OSS 20B vs Claude Opus 4.6GPT-OSS 20B vs GPT-5.3 CodexGPT-OSS 20B vs Grok 4.1GPT-OSS 20B vs GPT-5.2