Model comparison

GPT-4.1 vs Qwen3-4B

GPT-4.1 is the stronger model overall, scoring 35.9 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 5 shared benchmarks.

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

They share 5 benchmarks with published results for both. GPT-4.1 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 11.7.
The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 54% for GPT-4.1 and 35.7% for Qwen3-4B.
Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 and Qwen3-4B specifications
	GPT-4.1	Qwen3-4B
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	35.9	31.9
Released	2025-04-14	2025-04-29
Weights	Proprietary	Open
Context window	1.05M	—
Max output	33K	—
Input $ / M tokens	$2	—
Output $ / M tokens	$8	—
Results tracked	52	6

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

Category by category

Coding Not comparable

GPT-4.1: 34.4 (#238), Qwen3-4B: —

Coding benchmarks
Benchmark	GPT-4.1	Qwen3-4B
SWE-bench Verified	48.5%	—
SWE-bench Verified (bash only)	39.6%	—
Aider Polyglot	52.4%	—
WeirdML	39%	—
LMArena Coding	1391	—
CadEval	42%	—
ALE-Bench	558.1	—

Agentic & Tool Use GPT-4.1 leads

GPT-4.1: 34.7 (#43), Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
Benchmark	GPT-4.1	Qwen3-4B
Berkeley Function Calling Leaderboard	54%	35.7%

Reasoning Qwen3-4B leads

GPT-4.1: 11.7 (#339), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
Benchmark	GPT-4.1	Qwen3-4B
Chess Puzzles	6%	4%
ARC-AGI-2	0.4%	—
SimpleBench	27%	—
Kagi LLM Benchmark	52.3%	—
ARC-AGI-1	5.5%	—
EnigmaEval	2.2%	—
LMArena Hard Prompts	1384	—
DTBench	68.3%	—
LMCA	25.6%	—
Epoch Capabilities Index	136.78	—
ForecastBench	61.5	—

Math Qwen3-4B leads

GPT-4.1: 22.3 (#280), Qwen3-4B: 29.7 (#240)

Math benchmarks
Benchmark	GPT-4.1	Qwen3-4B
OTIS Mock AIME 2024-2025	38.3%	52.2%
FrontierMath (Tiers 1-3)	6%	—
MathArena Final-Answer Competitions	—	38.5%
Omni-MATH	47.1%	—
LMArena Math	1370	—
MATH Level 5	83%	—
FrontierMath (Feb 2025 set)	5.5%	—
FrontierMath Tier 4 (v1)	0%	—

Knowledge GPT-4.1 leads

GPT-4.1: 37.1 (#160), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
Benchmark	GPT-4.1	Qwen3-4B
GPQA Diamond	66.9%	52.3%
Vectara Hallucination Rate	5.6%	5.7%
Humanity's Last Exam	5.4%	—
SimpleQA Verified	31.1%	—
MMLU-Pro	81.1%	—
GPQA (HELM)	65.9%	—
LMArena Expert	1364	—

Multimodal Not comparable

GPT-4.1: 38.2 (#67), Qwen3-4B: —

Multimodal benchmarks
Benchmark	GPT-4.1	Qwen3-4B
LMArena Vision	1211	—
GeoBench	72%	—

Multilingual Not comparable

GPT-4.1: 49.4 (#133), Qwen3-4B: —

Multilingual benchmarks
Benchmark	GPT-4.1	Qwen3-4B
LMArena Non-English	1370	—
LMArena Chinese	1382	—
LMArena French	1382	—
LMArena German	1381	—
LMArena Japanese	1319	—
LMArena Korean	1339	—
LMArena Russian	1377	—
LMArena Spanish	1376	—

Instruction Following Not comparable

GPT-4.1: 71.3 (#153), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	GPT-4.1	Qwen3-4B
IFEval	83.8%	—
LMArena Instruction Following	1367	—

Long Context Not comparable

GPT-4.1: 40.0 (#163), Qwen3-4B: —

Long Context benchmarks
Benchmark	GPT-4.1	Qwen3-4B
Fiction.LiveBench	63.9%	—
LMArena Longer Query	1385	—

Writing & Preference Not comparable

GPT-4.1: 57.6 (#125), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	GPT-4.1	Qwen3-4B
LMArena Text	1383	—
LMArena Creative Writing	1363	—
EQ-Bench Creative Writing	1420	—
WildBench	85.4%	—
LMArena Multi-Turn	1398	—

Frequently asked questions

Is GPT-4.1 better than Qwen3-4B?