Qwen3 235B 2507 (Reasoning) vs Z-1

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

Quick Verdict

Z-1 wins overall with a score of 43 vs 31 (12 point difference).Z-1 wins 4 out of 4 categories.

Knowledge

Z-1

Qwen3 235B 2507 (Reasoning)

37.8

Z-1

49.8

40
MMLU
52
39
GPQA
51
37
SuperGPQA
49
35
OpenBookQA
47

Coding

Z-1

Qwen3 235B 2507 (Reasoning)

32

Z-1

44

32
HumanEval
44

Mathematics

Z-1

Qwen3 235B 2507 (Reasoning)

39

Z-1

51

40
AIME 2023
52
42
AIME 2024
54
41
AIME 2025
53
36
HMMT Feb 2023
48
38
HMMT Feb 2024
50
37
HMMT Feb 2025
49
39
BRUMO 2025
51

Reasoning

Z-1

Qwen3 235B 2507 (Reasoning)

37

Z-1

49

38
SimpleQA
50
36
MuSR
48

Frequently Asked Questions

Which is better, Qwen3 235B 2507 (Reasoning) or Z-1?

Z-1 scores higher overall with 43 vs 31, a difference of 12 points across all benchmarks.

Which is better for knowledge tasks, Qwen3 235B 2507 (Reasoning) or Z-1?

Z-1 leads in knowledge tasks with an average score of 49.8 vs 37.8.

Which is better for coding, Qwen3 235B 2507 (Reasoning) or Z-1?

Z-1 leads in coding with an average score of 44 vs 32.

Which is better for math, Qwen3 235B 2507 (Reasoning) or Z-1?

Z-1 leads in math with an average score of 51 vs 39.

Which is better for reasoning, Qwen3 235B 2507 (Reasoning) or Z-1?

Z-1 leads in reasoning with an average score of 49 vs 37.