Model comparison

Qwen2.5-Coder (1.5B) vs Qwen3 32B

Qwen3 32B has enough public results to be ranked (#166); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

Last verified October 10, 2026. 1 shared benchmarks.

Qwen2.5-Coder (1.5B)

Alibaba (Qwen)

—

Unranked

Qwen3 32B

Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

They share 1 benchmark with published results for both.

Side by side

Qwen2.5-Coder (1.5B) and Qwen3 32B specifications
	Qwen2.5-Coder (1.5B)	Qwen3 32B
Provider	Alibaba (Qwen)	Alibaba (Qwen)
Noometry Index	—	38.8
Released	2024-09-18	2025-04
Weights	Open	Open
Context window	—	131K
Max output	—	16K
Input $ / M tokens	—	$0.70
Output $ / M tokens	—	$2.80
Results tracked	6	26

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

Category by category

Coding Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 37.3 (#184)

Coding benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
Aider Polyglot	—	40%
SciCode	—	35.4%
LMArena Coding	—	1358

Agentic & Tool Use Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 32.3 (#58)

Agentic & Tool Use benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
Berkeley Function Calling Leaderboard	—	48.7%

Reasoning Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 19.6 (#233)

Reasoning benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
Epoch Capabilities Index	112.93	138.51
Kagi LLM Benchmark	—	54.9%
CritPt	—	0.3%
Chess Puzzles	—	5%
LMArena Hard Prompts	—	1335
DTBench	—	67.5%
LMCA	—	17.3%
HellaSwag	76.8%	—
WinoGrande	72.9%	—

Math Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 37.9 (#89)

Math benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
OTIS Mock AIME 2024-2025	—	66.9%
LMArena Math	—	1399
GSM8K	86.7%	—

Knowledge Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 40.0 (#112)

Knowledge benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
GPQA Diamond	—	65.7%
Vectara Hallucination Rate	—	5.9%
LMArena Expert	—	1362
ARC (AI2) Challenge	60.9%	—
MMLU	68%	—

Multilingual Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 45.8 (#162)

Multilingual benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
LMArena Non-English	—	1317
LMArena Chinese	—	1357
LMArena German	—	1341
LMArena Russian	—	1311

Instruction Following Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 69.1 (#174)

Instruction Following benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
LMArena Instruction Following	—	1305

Long Context Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 43.7 (#83)

Long Context benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
Fiction.LiveBench	—	74.2%
LMArena Longer Query	—	1327

Writing & Preference Not comparable

Qwen2.5-Coder (1.5B): —, Qwen3 32B: 53.1 (#158)

Writing & Preference benchmarks
Benchmark	Qwen2.5-Coder (1.5B)	Qwen3 32B
LMArena Text	—	1340
LMArena Creative Writing	—	1297
LMArena Multi-Turn	—	1331

Frequently asked questions

Is Qwen2.5-Coder (1.5B) better than Qwen3 32B?