benchlm.ai

o4-mini (high) vs Qwen3 235B 2507

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

Quick Verdict

o4-mini (high) wins overall with a score of 65 vs 30 (35 point difference).o4-mini (high) wins 4 out of 4 categories.

o4-mini (high)

CreatorOpenAI
TypeProprietary
Context200K
Score65

Qwen3 235B 2507

CreatorAlibaba
TypeOpen Weight
Context128K
Score30

Knowledge

o4-mini (high)

o4-mini (high)

80.5

Qwen3 235B 2507

36.8

82
MMLU
39
82
GPQA
38
80
SuperGPQA
36
78
OpenBookQA
34

Coding

o4-mini (high)

o4-mini (high)

74

Qwen3 235B 2507

31

74
HumanEval
31

Mathematics

o4-mini (high)

o4-mini (high)

82

Qwen3 235B 2507

38

83
AIME 2023
39
85
AIME 2024
41
84
AIME 2025
40
79
HMMT Feb 2023
35
81
HMMT Feb 2024
37
80
HMMT Feb 2025
36
82
BRUMO 2025
38

Reasoning

o4-mini (high)

o4-mini (high)

79

Qwen3 235B 2507

36

80
SimpleQA
37
78
MuSR
35

Frequently Asked Questions

Which is better, o4-mini (high) or Qwen3 235B 2507?

o4-mini (high) scores higher overall with 65 vs 30, a difference of 35 points across all benchmarks.

Which is better for knowledge tasks, o4-mini (high) or Qwen3 235B 2507?

o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 36.8.

Which is better for coding, o4-mini (high) or Qwen3 235B 2507?

o4-mini (high) leads in coding with an average score of 74 vs 31.

Which is better for math, o4-mini (high) or Qwen3 235B 2507?

o4-mini (high) leads in math with an average score of 82 vs 38.

Which is better for reasoning, o4-mini (high) or Qwen3 235B 2507?

o4-mini (high) leads in reasoning with an average score of 79 vs 36.

Related Comparisons

o4-mini (high) vs GPT-5.4o4-mini (high) vs Gemini 3.1 Proo4-mini (high) vs Claude Opus 4.6o4-mini (high) vs GPT-5.3 Codexo4-mini (high) vs Grok 4.1o4-mini (high) vs GPT-5.2