Noometry

Model comparison

o1-mini vs Qwen3.5 27B

Qwen3.5 27B is the stronger model overall, scoring 41.9 to 34.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 Confirmed

Qwen3.5 27B Alibaba (Qwen)

41.9

Rank #127 Confirmed

Summary

  • They share 18 benchmarks with published results for both. o1-mini scores higher in 0 categories and Qwen3.5 27B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5 27B leads 27.5 to 8.8.
  • Qwen3.5 27B has downloadable open weights; the other is API-only.

Side by side

o1-miniQwen3.5 27B
ProviderOpenAIAlibaba (Qwen)
Noometry Index34.041.9
Released2024-09-122026-02-23
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.30
Output $ / M tokens—$2.40
Results tracked3928

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

Category by category

Coding Qwen3.5 27B leads

o1-mini: 35.5 (#224), Qwen3.5 27B: 38.9 (#168)

Benchmarko1-miniQwen3.5 27B
WeirdML36.3%39.5%
LMArena Coding13621427
Aider Polyglot32.9%—
LMArena WebDev—1358
LiveBench Coding48%—
ALE-Bench—349.45
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Not comparable

o1-mini: 24.6 (#118), Qwen3.5 27B: —

Benchmarko1-miniQwen3.5 27B
Cybench10%—
Vending-Bench 2—201.98

Reasoning Qwen3.5 27B leads

o1-mini: 8.8 (#346), Qwen3.5 27B: 27.5 (#117)

Benchmarko1-miniQwen3.5 27B
LMArena Hard Prompts13331414
ARC-AGI-20.8%—
SimpleBench18.1%—
NYT Connections (extended)—47.9%
ARC-AGI-114%—
Thematic Generalization—45.5%
LiveBench Reasoning72.3%—
DTBench—82.4%
LiveBench Data Analysis57.9%—
LMCA—34%
Epoch Capabilities Index135.82—
LiveBench57.8%—

Math Qwen3.5 27B leads

o1-mini: 35.4 (#186), Qwen3.5 27B: 38.8 (#127)

Benchmarko1-miniQwen3.5 27B
LMArena Math13581429
MathArena Final-Answer Competitions—56.7%
OTIS Mock AIME 2024-202546.9%—
LiveBench Math62%—
MATH Level 589.2%—
FrontierMath (Feb 2025 set)1.7%—

Knowledge Qwen3.5 27B leads

o1-mini: 34.9 (#192), Qwen3.5 27B: 38.0 (#150)

Benchmarko1-miniQwen3.5 27B
LMArena Expert13161428
GPQA Diamond62.4%—
Confabulations18.6%—
Vectara Hallucination Rate—12.1%

Multimodal Not comparable

o1-mini: —, Qwen3.5 27B: 39.4 (#59)

Benchmarko1-miniQwen3.5 27B
LMArena Vision—1241

Multilingual Qwen3.5 27B leads

o1-mini: 43.6 (#182), Qwen3.5 27B: 50.8 (#115)

Benchmarko1-miniQwen3.5 27B
LMArena Non-English12891390
LMArena Chinese13141478
LMArena French12931410
LMArena German12781393
LMArena Japanese12451345
LMArena Korean12231358
LMArena Russian12831390
LMArena Spanish13031407

Instruction Following Qwen3.5 27B leads

o1-mini: 66.7 (#206), Qwen3.5 27B: 73.5 (#119)

Benchmarko1-miniQwen3.5 27B
LMArena Instruction Following13041393
LiveBench Instruction Following65.4%—

Long Context Qwen3.5 27B leads

o1-mini: 40.1 (#161), Qwen3.5 27B: 43.1 (#106)

Benchmarko1-miniQwen3.5 27B
LMArena Longer Query13201413

Writing & Preference Qwen3.5 27B leads

o1-mini: 48.4 (#202), Qwen3.5 27B: 59.3 (#111)

Benchmarko1-miniQwen3.5 27B
LMArena Text13171409
LMArena Creative Writing12441362
LMArena Multi-Turn13141410
Short-Story Creative Writing64.9%—
LiveBench Language40.9%—

Frequently asked questions

Is o1-mini better than Qwen3.5 27B?

Qwen3.5 27B is the stronger model overall, scoring 41.9 to 34.0 on the Noometry Index.

Is o1-mini or Qwen3.5 27B better for coding?

Qwen3.5 27B scores higher on coding benchmarks: 38.9 versus 35.5 in the Noometry coding category.

How many benchmarks do o1-mini and Qwen3.5 27B share?

18 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen3.5 27B has 28.

Related comparisons

Go deeper