Kimi K2.5 vs Qwen3 235B 2507 (Reasoning)

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

Quick Verdict

Kimi K2.5 wins overall with a score of 62 vs 31 (31 point difference).Kimi K2.5 wins 4 out of 4 categories.

Knowledge

Kimi K2.5

Kimi K2.5

74.8

Qwen3 235B 2507 (Reasoning)

37.8

77
MMLU
40
76
GPQA
39
74
SuperGPQA
37
72
OpenBookQA
35

Coding

Kimi K2.5

Kimi K2.5

69

Qwen3 235B 2507 (Reasoning)

32

69
HumanEval
32

Mathematics

Kimi K2.5

Kimi K2.5

76

Qwen3 235B 2507 (Reasoning)

39

77
AIME 2023
40
79
AIME 2024
42
78
AIME 2025
41
73
HMMT Feb 2023
36
75
HMMT Feb 2024
38
74
HMMT Feb 2025
37
76
BRUMO 2025
39

Reasoning

Kimi K2.5

Kimi K2.5

73

Qwen3 235B 2507 (Reasoning)

37

74
SimpleQA
38
72
MuSR
36

Frequently Asked Questions

Which is better, Kimi K2.5 or Qwen3 235B 2507 (Reasoning)?

Kimi K2.5 scores higher overall with 62 vs 31, a difference of 31 points across all benchmarks.

Which is better for knowledge tasks, Kimi K2.5 or Qwen3 235B 2507 (Reasoning)?

Kimi K2.5 leads in knowledge tasks with an average score of 74.8 vs 37.8.

Which is better for coding, Kimi K2.5 or Qwen3 235B 2507 (Reasoning)?

Kimi K2.5 leads in coding with an average score of 69 vs 32.

Which is better for math, Kimi K2.5 or Qwen3 235B 2507 (Reasoning)?

Kimi K2.5 leads in math with an average score of 76 vs 39.

Which is better for reasoning, Kimi K2.5 or Qwen3 235B 2507 (Reasoning)?

Kimi K2.5 leads in reasoning with an average score of 73 vs 37.