Model comparison

GPT-5.2 vs Qwen3-4B

GPT-5.2 is the stronger model overall, scoring 54.1 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 6 shared benchmarks.

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

They share 6 benchmarks with published results for both. GPT-5.2 scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-5.2 leads 50.2 to 19.2.
The biggest single-benchmark swing is Chess Puzzles: 49% for GPT-5.2 and 4% for Qwen3-4B.
Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 and Qwen3-4B specifications
	GPT-5.2	Qwen3-4B
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	54.1	31.9
Released	2025-12-11	2025-04-29
Weights	Proprietary	Open
Context window	400K	—
Max output	128K	—
Input $ / M tokens	$1.75	—
Output $ / M tokens	$14	—
Results tracked	67	6

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

Category by category

Coding Not comparable

GPT-5.2: 51.6 (#37), Qwen3-4B: —

Coding benchmarks
Benchmark	GPT-5.2	Qwen3-4B
SWE-bench Verified	73.8%	—
SWE-bench Verified (bash only)	72.8%	—
LMArena WebDev	1416	—
SWE-bench Multilingual	66.7%	—
GSO	27.4%	—
WeirdML	72.2%	—
LMArena Coding	1447	—
ALE-Bench	1,294	—
AlgoTune	2.05	—

Agentic & Tool Use GPT-5.2 leads

GPT-5.2: 40.2 (#24), Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.2	Qwen3-4B
Berkeley Function Calling Leaderboard	55.9%	35.7%
Terminal-Bench	64.9%	—
GDPval	49.7%	—
Remote Labor Index	2.5%	—
τ²-bench Airline	83%	—
τ²-bench Banking	32.2%	—
τ²-bench Retail	81.6%	—
τ²-bench Telecom	89.7%	—
DeepResearch Bench	41.1%	—
LMArena Search	1207	—
METR Time Horizons	75.3%	—
Vending-Bench 2	3,591	—

Reasoning GPT-5.2 leads

GPT-5.2: 50.2 (#35), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
Benchmark	GPT-5.2	Qwen3-4B
Chess Puzzles	49%	4%
ARC-AGI-2	52.9%	—
SimpleBench	45.8%	—
Kagi LLM Benchmark	73.3%	—
NYT Connections (extended)	83.6%	—
ARC-AGI-1	86.2%	—
EnigmaEval	10.4%	—
EBR-Bench	23%	—
LMArena Hard Prompts	1445	—
Mystery Game Puzzles	23%	—
DTBench	90.9%	—
LMCA	43.9%	—
Epoch Capabilities Index	153.45	—
ForecastBench	60.1	—

Math GPT-5.2 leads

GPT-5.2: 60.0 (#38), Qwen3-4B: 29.7 (#240)

Math benchmarks
Benchmark	GPT-5.2	Qwen3-4B
MathArena Final-Answer Competitions	72%	38.5%
OTIS Mock AIME 2024-2025	96.1%	52.2%
FrontierMath (Tiers 1-3)	67.4%	—
FrontierMath Tier 4	31.7%	—
ProofBench	15%	—
LMArena Math	1440	—
FrontierMath (Feb 2025 set)	40.7%	—
FrontierMath Tier 4 (v1)	18.8%	—

Knowledge GPT-5.2 leads

GPT-5.2: 59.3 (#32), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
Benchmark	GPT-5.2	Qwen3-4B
GPQA Diamond	91.4%	52.3%
Vectara Hallucination Rate	8.4%	5.7%
Humanity's Last Exam	27.8%	—
SimpleQA Verified	37.1%	—
LMArena Expert	1445	—

Multimodal Not comparable

GPT-5.2: 51.3 (#7), Qwen3-4B: —

Multimodal benchmarks
Benchmark	GPT-5.2	Qwen3-4B
LMArena Vision	1268	—
VPCT	84%	—
Furniture Assembly	38.3%	—
LMArena Document	1405	—

Multilingual Not comparable

GPT-5.2: 53.4 (#67), Qwen3-4B: —

Multilingual benchmarks
Benchmark	GPT-5.2	Qwen3-4B
LMArena Non-English	1425	—
LMArena Chinese	1460	—
LMArena French	1455	—
LMArena German	1448	—
LMArena Japanese	1420	—
LMArena Korean	1392	—
LMArena Russian	1440	—
LMArena Spanish	1433	—

Instruction Following Not comparable

GPT-5.2: 74.7 (#89), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	GPT-5.2	Qwen3-4B
LMArena Instruction Following	1417	—

Long Context Not comparable

GPT-5.2: 44.0 (#78), Qwen3-4B: —

Long Context benchmarks
Benchmark	GPT-5.2	Qwen3-4B
CL-bench	18.2%	—
LMArena Longer Query	1428	—

Writing & Preference Not comparable

GPT-5.2: 66.8 (#32), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	GPT-5.2	Qwen3-4B
LMArena Text	1439	—
LMArena Creative Writing	1401	—
EQ-Bench Creative Writing	1703	—
LMArena Multi-Turn	1458	—

Frequently asked questions

Is GPT-5.2 better than Qwen3-4B?