Model comparison

Qwen3-1.7B vs Qwen3 32B

Qwen3 32B is the stronger model overall, scoring 38.8 to 26.2 on the Noometry Index.

Last verified October 10, 2026. 4 shared benchmarks.

Qwen3-1.7B

Alibaba (Qwen)

26.2

Rank #331 Reported

Qwen3 32B

Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

They share 4 benchmarks with published results for both. Qwen3-1.7B scores higher in 0 categories and Qwen3 32B in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where Qwen3 32B leads 37.9 to 15.4.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.1% for Qwen3-1.7B and 66.9% for Qwen3 32B.

Side by side

Qwen3-1.7B and Qwen3 32B specifications
	Qwen3-1.7B	Qwen3 32B
Provider	Alibaba (Qwen)	Alibaba (Qwen)
Noometry Index	26.2	38.8
Released	2025-04-29	2025-04
Weights	Open	Open
Context window	—	131K
Max output	—	16K
Input $ / M tokens	—	$0.70
Output $ / M tokens	—	$2.80
Results tracked	4	26

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

Category by category

Coding Not comparable

Qwen3-1.7B: —, Qwen3 32B: 37.3 (#184)

Coding benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
Aider Polyglot	—	40%
SciCode	—	35.4%
LMArena Coding	—	1358

Agentic & Tool Use Qwen3 32B leads

Qwen3-1.7B: 24.5 (#108), Qwen3 32B: 32.3 (#58)

Agentic & Tool Use benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
Berkeley Function Calling Leaderboard	28.4%	48.7%

Reasoning Qwen3 32B leads

Qwen3-1.7B: 18.5 (#263), Qwen3 32B: 19.6 (#233)

Reasoning benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
Chess Puzzles	0%	5%
Kagi LLM Benchmark	—	54.9%
CritPt	—	0.3%
LMArena Hard Prompts	—	1335
DTBench	—	67.5%
LMCA	—	17.3%
Epoch Capabilities Index	—	138.51

Math Qwen3 32B leads

Qwen3-1.7B: 15.4 (#288), Qwen3 32B: 37.9 (#89)

Math benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
OTIS Mock AIME 2024-2025	8.1%	66.9%
LMArena Math	—	1399

Knowledge Qwen3 32B leads

Qwen3-1.7B: 19.6 (#273), Qwen3 32B: 40.0 (#112)

Knowledge benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
GPQA Diamond	38%	65.7%
Vectara Hallucination Rate	—	5.9%
LMArena Expert	—	1362

Multilingual Not comparable

Qwen3-1.7B: —, Qwen3 32B: 45.8 (#162)

Multilingual benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
LMArena Non-English	—	1317
LMArena Chinese	—	1357
LMArena German	—	1341
LMArena Russian	—	1311

Instruction Following Not comparable

Qwen3-1.7B: —, Qwen3 32B: 69.1 (#174)

Instruction Following benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
LMArena Instruction Following	—	1305

Long Context Not comparable

Qwen3-1.7B: —, Qwen3 32B: 43.7 (#83)

Long Context benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
Fiction.LiveBench	—	74.2%
LMArena Longer Query	—	1327

Writing & Preference Not comparable

Qwen3-1.7B: —, Qwen3 32B: 53.1 (#158)

Writing & Preference benchmarks
Benchmark	Qwen3-1.7B	Qwen3 32B
LMArena Text	—	1340
LMArena Creative Writing	—	1297
LMArena Multi-Turn	—	1331

Frequently asked questions

Is Qwen3-1.7B better than Qwen3 32B?