Noometry

Model comparison

o1-mini vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 34.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 Confirmed

Qwen3.8 27B Alibaba (Qwen)

46.0

Rank #68 Confirmed

Summary

  • They share 20 benchmarks with published results for both. o1-mini scores higher in 0 categories and Qwen3.8 27B in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 8.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 14% for o1-mini and 87.5% for Qwen3.8 27B.
  • Qwen3.8 27B has downloadable open weights; the other is API-only.

Side by side

o1-miniQwen3.8 27B
ProviderOpenAIAlibaba (Qwen)
Noometry Index34.046.0
Released2024-09-122026-08-14
WeightsProprietaryOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.04
Output $ / M tokens—$2.30
Results tracked3931

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

Category by category

Coding Qwen3.8 27B leads

o1-mini: 35.5 (#224), Qwen3.8 27B: 50.5 (#44)

Benchmarko1-miniQwen3.8 27B
LMArena Coding13621482
Aider Polyglot32.9%—
LMArena WebDev—1593
SciCode—46.6%
WeirdML36.3%—
LiveBench Coding48%—
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Qwen3.8 27B leads

o1-mini: 24.6 (#118), Qwen3.8 27B: 32.9 (#57)

Benchmarko1-miniQwen3.8 27B
APEX-Agents—47.5%
Cybench10%—

Reasoning Qwen3.8 27B leads

o1-mini: 8.8 (#346), Qwen3.8 27B: 41.0 (#54)

Benchmarko1-miniQwen3.8 27B
ARC-AGI-20.8%42.4%
ARC-AGI-114%87.5%
LMArena Hard Prompts13331460
Epoch Capabilities Index135.82149.38
SimpleBench18.1%—
NYT Connections (extended)—54.5%
CritPt—5.4%
LiveBench Reasoning72.3%—
DTBench—88%
LiveBench Data Analysis57.9%—
LMCA—41.4%
Surface Evolver Bench—45%
LiveBench57.8%—

Math Qwen3.8 27B leads

o1-mini: 35.4 (#186), Qwen3.8 27B: 37.1 (#161)

Benchmarko1-miniQwen3.8 27B
LMArena Math13581456
OTIS Mock AIME 2024-202546.9%—
ProofBench—16%
LiveBench Math62%—
MATH Level 589.2%—
FrontierMath (Feb 2025 set)1.7%—

Knowledge Qwen3.8 27B leads

o1-mini: 34.9 (#192), Qwen3.8 27B: 41.6 (#109)

Benchmarko1-miniQwen3.8 27B
LMArena Expert13161482
GPQA Diamond62.4%—
Confabulations18.6%—

Multimodal Not comparable

o1-mini: —, Qwen3.8 27B: 41.3 (#37)

Benchmarko1-miniQwen3.8 27B
LMArena Vision—1271

Multilingual Qwen3.8 27B leads

o1-mini: 43.6 (#182), Qwen3.8 27B: 53.7 (#60)

Benchmarko1-miniQwen3.8 27B
LMArena Non-English12891430
LMArena Chinese13141504
LMArena French12931465
LMArena German12781438
LMArena Japanese12451384
LMArena Korean12231393
LMArena Russian12831415
LMArena Spanish13031448

Instruction Following Qwen3.8 27B leads

o1-mini: 66.7 (#206), Qwen3.8 27B: 75.8 (#53)

Benchmarko1-miniQwen3.8 27B
LMArena Instruction Following13041439
LiveBench Instruction Following65.4%—

Long Context Qwen3.8 27B leads

o1-mini: 40.1 (#161), Qwen3.8 27B: 44.3 (#70)

Benchmarko1-miniQwen3.8 27B
LMArena Longer Query13201450

Writing & Preference Qwen3.8 27B leads

o1-mini: 48.4 (#202), Qwen3.8 27B: 65.8 (#43)

Benchmarko1-miniQwen3.8 27B
LMArena Text13171441
LMArena Creative Writing12441384
LMArena Multi-Turn13141441
Short-Story Creative Writing64.9%—
EQ-Bench Creative Writing—1671
LiveBench Language40.9%—

Frequently asked questions

Is o1-mini better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 34.0 on the Noometry Index.

Is o1-mini or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 35.5 in the Noometry coding category.

How many benchmarks do o1-mini and Qwen3.8 27B share?

20 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen3.8 27B has 31.

Related comparisons

Go deeper