Noometry

Model comparison

o1-mini vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.0 on the Noometry Index.

Last verified . 29 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 29 benchmarks with published results for both. o1-mini scores higher in 0 categories and Qwen3 235B-A22B in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 35.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 46.9% for o1-mini and 86.7% for Qwen3 235B-A22B.
  • Qwen3 235B-A22B has downloadable open weights; the other is API-only.

Side by side

o1-miniQwen3 235B-A22B
ProviderOpenAIAlibaba (Qwen)
Noometry Index34.043.5
Released2024-09-122025-04
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked3949

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3 235B-A22B leads

o1-mini: 35.5 (#224), Qwen3 235B-A22B: 44.3 (#75)

Benchmarko1-miniQwen3 235B-A22B
Aider Polyglot32.9%59.6%
WeirdML36.3%41%
LMArena Coding13621445
SciCode—42.4%
LiveBench Coding48%—
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Qwen3 235B-A22B leads

o1-mini: 24.6 (#118), Qwen3 235B-A22B: 33.9 (#51)

Benchmarko1-miniQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Cybench10%—
Vending-Bench 2—-11.34

Reasoning Qwen3 235B-A22B leads

o1-mini: 8.8 (#346), Qwen3 235B-A22B: 15.7 (#311)

Benchmarko1-miniQwen3 235B-A22B
ARC-AGI-20.8%1.3%
SimpleBench18.1%31%
ARC-AGI-114%11%
LMArena Hard Prompts13331433
Epoch Capabilities Index135.82143.85
Kagi LLM Benchmark—69.4%
CritPt—0%
Chess Puzzles—12%
LiveBench Reasoning72.3%—
Mystery Game Puzzles—9%
DTBench—80.3%
LiveBench Data Analysis57.9%—
LMCA—29.3%
ForecastBench—59.7
LiveBench57.8%—

Math Qwen3 235B-A22B leads

o1-mini: 35.4 (#186), Qwen3 235B-A22B: 50.4 (#57)

Benchmarko1-miniQwen3 235B-A22B
OTIS Mock AIME 2024-202546.9%86.7%
LMArena Math13581432
MATH Level 589.2%68.9%
FrontierMath (Feb 2025 set)1.7%8.5%
Omni-MATH—71.8%
LiveBench Math62%—
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

o1-mini: 34.9 (#192), Qwen3 235B-A22B: 49.6 (#73)

Benchmarko1-miniQwen3 235B-A22B
GPQA Diamond62.4%80.1%
Confabulations18.6%15.6%
LMArena Expert13161463
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—72.7%

Multilingual Qwen3 235B-A22B leads

o1-mini: 43.6 (#182), Qwen3 235B-A22B: 52.3 (#89)

Benchmarko1-miniQwen3 235B-A22B
LMArena Non-English12891409
LMArena Chinese13141481
LMArena French12931445
LMArena German12781433
LMArena Japanese12451399
LMArena Korean12231391
LMArena Russian12831411
LMArena Spanish13031430

Instruction Following Qwen3 235B-A22B leads

o1-mini: 66.7 (#206), Qwen3 235B-A22B: 72.6 (#136)

Benchmarko1-miniQwen3 235B-A22B
LMArena Instruction Following13041408
LiveBench Instruction Following65.4%—
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

o1-mini: 40.1 (#161), Qwen3 235B-A22B: 46.1 (#26)

Benchmarko1-miniQwen3 235B-A22B
LMArena Longer Query13201426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

o1-mini: 48.4 (#202), Qwen3 235B-A22B: 59.6 (#108)

Benchmarko1-miniQwen3 235B-A22B
LMArena Text13171419
LMArena Creative Writing12441384
Short-Story Creative Writing64.9%83%
LMArena Multi-Turn13141432
EQ-Bench Creative Writing—1366
WildBench—86.6%
LiveBench Language40.9%—

Frequently asked questions

Is o1-mini better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.0 on the Noometry Index.

Is o1-mini or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 35.5 in the Noometry coding category.

How many benchmarks do o1-mini and Qwen3 235B-A22B share?

29 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper