Qwen3 235B 2507 (Reasoning) vs o1-pro

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

Qwen3 235B 2507 (Reasoning) is clearly ahead on the aggregate, 40 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

o1-pro gives you the larger context window at 200K, compared with 128K for Qwen3 235B 2507 (Reasoning).

Quick Verdict

Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. o1-pro only becomes the better choice if mathematics is the priority or you need the larger 200K context window.

Knowledge

o1-pro

Qwen3 235B 2507 (Reasoning)

34.7

o1-pro

79

40
MMLU
-
39
GPQA
79
37
SuperGPQA
-
35
OpenBookQA
-
51
MMLU-Pro
-
6
HLE
-

Coding

Qwen3 235B 2507 (Reasoning)
32
HumanEval
-
16
SWE-bench Verified
-
18
LiveCodeBench
-

Mathematics

o1-pro

Qwen3 235B 2507 (Reasoning)

41.6

o1-pro

86

40
AIME 2023
-
42
AIME 2024
86
41
AIME 2025
-
36
HMMT Feb 2023
-
38
HMMT Feb 2024
-
37
HMMT Feb 2025
-
39
BRUMO 2025
-
60
MATH-500
-

Reasoning

Qwen3 235B 2507 (Reasoning)
38
SimpleQA
-
36
MuSR
-
63
BBH
-

Instruction Following

Qwen3 235B 2507 (Reasoning)
68
IFEval
-

Multilingual

Qwen3 235B 2507 (Reasoning)
62
MGSM
-

Frequently Asked Questions

Which is better, Qwen3 235B 2507 (Reasoning) or o1-pro?

Qwen3 235B 2507 (Reasoning) is ahead overall, 40 to 33. The biggest single separator in this matchup is AIME 2024, where the scores are 42 and 86.

Which is better for knowledge tasks, Qwen3 235B 2507 (Reasoning) or o1-pro?

o1-pro has the edge for knowledge tasks in this comparison, averaging 79 versus 34.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3 235B 2507 (Reasoning) or o1-pro?

o1-pro has the edge for math in this comparison, averaging 86 versus 41.6. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.

Last updated: March 9, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.