Model comparison

GPT-6 Sol vs Qwen3-4B

GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 3 shared benchmarks.

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Qwen3-4B

Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

They share 3 benchmarks with published results for both. GPT-6 Sol scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-6 Sol leads 87.2 to 29.7.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6 Sol and 52.2% for Qwen3-4B.
Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

GPT-6 Sol and Qwen3-4B specifications
	GPT-6 Sol	Qwen3-4B
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	61.8	31.9
Released	2026-09-22	2025-04-29
Weights	Proprietary	Open
Context window	1.05M	—
Max output	128K	—
Input $ / M tokens	$2	—
Output $ / M tokens	$10	—
Results tracked	45	6

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

Category by category

Coding Not comparable

GPT-6 Sol: 60.1 (#11), Qwen3-4B: —

Coding benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
DeepSWE	68.8%	—
FrontierCode	49.3%	—
LMArena WebDev	1688	—
SciCode	57.6%	—
LMArena Coding	1447	—
ALE-Bench	2,462	—

Agentic & Tool Use GPT-6 Sol leads

GPT-6 Sol: 37.2 (#36), Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
APEX-Agents	54.3%	—
Berkeley Function Calling Leaderboard	—	35.7%
GDP.pdf	26.4%	—
Vending-Bench 2	14,428	—

Reasoning GPT-6 Sol leads

GPT-6 Sol: 74.0 (#9), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
ARC-AGI-2	89.6%	—
NYT Connections (extended)	90.1%	—
ARC-AGI-1	95.5%	—
CritPt	30.9%	—
Chess Puzzles	—	4%
EBR-Bench	53.3%	—
LMArena Hard Prompts	1418	—
Mystery Game Puzzles	56%	—
DTBench	97.3%	—
LMCA	59.1%	—
Epoch Capabilities Index	162.72	—

Math GPT-6 Sol leads

GPT-6 Sol: 87.2 (#7), Qwen3-4B: 29.7 (#240)

Math benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
OTIS Mock AIME 2024-2025	100%	52.2%
FrontierMath (Tiers 1-3)	89.8%	—
FrontierMath Tier 4	90%	—
MathArena Final-Answer Competitions	—	38.5%
ProofBench	83%	—
LMArena Math	1402	—

Knowledge GPT-6 Sol leads

GPT-6 Sol: 64.8 (#15), Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
GPQA Diamond	94.3%	52.3%
Vectara Hallucination Rate	6.5%	5.7%
SimpleQA Verified	60.7%	—
LMArena Expert	1439	—

Multimodal Not comparable

GPT-6 Sol: 47.6 (#10), Qwen3-4B: —

Multimodal benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
LMArena Vision	1245	—
Blueprint-Bench 2	36.9%	—
Furniture Assembly	58.3%	—

Multilingual Not comparable

GPT-6 Sol: 50.5 (#118), Qwen3-4B: —

Multilingual benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
LMArena Non-English	1385	—
LMArena Chinese	1405	—
LMArena French	1410	—
LMArena German	1390	—
LMArena Japanese	1385	—
LMArena Korean	1341	—
LMArena Russian	1401	—
LMArena Spanish	1384	—

Instruction Following Not comparable

GPT-6 Sol: 74.5 (#94), Qwen3-4B: —

Instruction Following benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
LMArena Instruction Following	1412	—

Long Context Not comparable

GPT-6 Sol: 43.1 (#108), Qwen3-4B: —

Long Context benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
LMArena Longer Query	1411	—

Writing & Preference Not comparable

GPT-6 Sol: 71.9 (#18), Qwen3-4B: —

Writing & Preference benchmarks
Benchmark	GPT-6 Sol	Qwen3-4B
LMArena Text	1395	—
LMArena Creative Writing	1378	—
EQ-Bench Creative Writing	2125	—
LMArena Multi-Turn	1412	—

Frequently asked questions

Is GPT-6 Sol better than Qwen3-4B?