Noometry

Model comparison

GPT-4.1 mini vs Qwen3-4B

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index.

Last verified . 4 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and Qwen3-4B in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3-4B leads 19.2 to 10.8.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 50.5% for GPT-4.1 mini and 35.7% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniQwen3-4B
ProviderOpenAIAlibaba (Qwen)
Noometry Index33.631.9
Released2025-04-142025-04-29
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked476

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

Category by category

Coding Not comparable

GPT-4.1 mini: 30.6 (#293), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
LMArena Coding1367—
CadEval16%—

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), Qwen3-4B: 27.6 (#100)

BenchmarkGPT-4.1 miniQwen3-4B
Berkeley Function Calling Leaderboard50.5%35.7%

Reasoning Qwen3-4B leads

GPT-4.1 mini: 10.8 (#340), Qwen3-4B: 19.2 (#268)

BenchmarkGPT-4.1 miniQwen3-4B
Chess Puzzles7%4%
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
LMArena Hard Prompts1349—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math Qwen3-4B leads

GPT-4.1 mini: 24.1 (#270), Qwen3-4B: 29.7 (#240)

BenchmarkGPT-4.1 miniQwen3-4B
OTIS Mock AIME 2024-202544.7%52.2%
FrontierMath (Tiers 1-3)6.7%—
MathArena Final-Answer Competitions—38.5%
Omni-MATH49.1%—
LMArena Math1343—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-4.1 mini leads

GPT-4.1 mini: 34.7 (#194), Qwen3-4B: 33.0 (#208)

BenchmarkGPT-4.1 miniQwen3-4B
GPQA Diamond65.8%52.3%
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
Vectara Hallucination Rate—5.7%
GPQA (HELM)61.4%—
LMArena Expert1338—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
LMArena Vision1181—

Multilingual Not comparable

GPT-4.1 mini: 45.7 (#166), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
LMArena Non-English1318—
LMArena Chinese1329—
LMArena French1358—
LMArena German1351—
LMArena Japanese1290—
LMArena Korean1298—
LMArena Russian1324—
LMArena Spanish1319—

Instruction Following Not comparable

GPT-4.1 mini: 73.7 (#118), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
IFEval90.4%—
LMArena Instruction Following1333—

Long Context Not comparable

GPT-4.1 mini: 31.8 (#275), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
Fiction.LiveBench44.4%—
LMArena Longer Query1344—

Writing & Preference Not comparable

GPT-4.1 mini: 48.6 (#199), Qwen3-4B: —

BenchmarkGPT-4.1 miniQwen3-4B
LMArena Text1340—
LMArena Creative Writing1300—
EQ-Bench Creative Writing1147—
WildBench83.8%—
LMArena Multi-Turn1354—

Frequently asked questions

Is GPT-4.1 mini better than Qwen3-4B?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index.

How many benchmarks do GPT-4.1 mini and Qwen3-4B share?

4 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper