Model comparison

DeepSeek-V3.2-Exp vs Qwen2.5 32B Instruct

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 29.7 on the Noometry Index.

Last verified October 10, 2026. 4 shared benchmarks.

DeepSeek-V3.2-Exp

DeepSeek

44.9

Rank #68 Confirmed

Qwen2.5 32B Instruct

Alibaba (Qwen)

29.7

Rank #291 Confirmed

Summary

They share 4 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 4 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 24.9.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 7.4% for Qwen2.5 32B Instruct.
DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 131K.

Side by side

DeepSeek-V3.2-Exp and Qwen2.5 32B Instruct specifications
	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	44.9	29.7
Released	2025-09-29	2024-09
Weights	Open	Open
Context window	164K	131K
Max output	66K	8K
Input $ / M tokens	$0.26	$0.70
Output $ / M tokens	$0.38	$2.80
Results tracked	48	7

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

Category by category

Coding DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 46.4 (#61), Qwen2.5 32B Instruct: 38.1 (#165)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
SWE-bench Verified (bash only)	70%	—
Aider Polyglot	74.2%	—
LMArena WebDev	1362	—
SWE-bench Multilingual	59%	—
SciCode	38.9%	—
WeirdML	39.5%	—
BigCodeBench Instruct	—	45%
LMArena Coding	1454	—
BigCodeBench Complete	—	52.3%

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 37.9 (#31), Qwen2.5 32B Instruct: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
Terminal-Bench	39.6%	—
Berkeley Function Calling Leaderboard	56.7%	—
TheAgentCompany	42.9%	—
Vending-Bench 2	1,034	—

Reasoning DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 22.0 (#185), Qwen2.5 32B Instruct: 18.5 (#262)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
Chess Puzzles	14%	0%
Epoch Capabilities Index	146.28	128.52
ARC-AGI-2	4%	—
Kagi LLM Benchmark	52.2%	—
NYT Connections (extended)	36.7%	—
ARC-AGI-1	57%	—
CritPt	2.9%	—
Thematic Generalization	65%	—
LMArena Hard Prompts	1433	—
DTBench	87.7%	—
LMCA	29.1%	—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 40.8 (#75), Qwen2.5 32B Instruct: 15.3 (#289)

Math benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
OTIS Mock AIME 2024-2025	87.8%	7.4%
MathArena Final-Answer Competitions	57.7%	—
ProofBench	8%	—
LMArena Math	1435	—
MATH Level 5	—	56.1%
FrontierMath (Feb 2025 set)	22.1%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.6 (#61), Qwen2.5 32B Instruct: 24.9 (#259)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
GPQA Diamond	83.4%	46.1%
Vectara Hallucination Rate	5.3%	—
LMArena Expert	1436	—

Multilingual Not comparable

DeepSeek-V3.2-Exp: 52.4 (#85), Qwen2.5 32B Instruct: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
LMArena Non-English	1409	—
LMArena Chinese	1461	—
LMArena French	1435	—
LMArena German	1440	—
LMArena Japanese	1377	—
LMArena Korean	1372	—
LMArena Russian	1423	—
LMArena Spanish	1441	—

Instruction Following Not comparable

DeepSeek-V3.2-Exp: 74.7 (#89), Qwen2.5 32B Instruct: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
LMArena Instruction Following	1413	—

Long Context Not comparable

DeepSeek-V3.2-Exp: 47.6 (#15), Qwen2.5 32B Instruct: —

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
Fiction.LiveBench	83.3%	—
CL-bench	13.2%	—
CL-bench Life	9.5%	—
LMArena Longer Query	1428	—

Writing & Preference Not comparable

DeepSeek-V3.2-Exp: 62.5 (#73), Qwen2.5 32B Instruct: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Exp	Qwen2.5 32B Instruct
LMArena Text	1425	—
LMArena Creative Writing	1403	—
EQ-Bench Creative Writing	1515	—
LMArena Multi-Turn	1427	—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Qwen2.5 32B Instruct?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 29.7 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Exp or Qwen2.5 32B Instruct?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.

Is DeepSeek-V3.2-Exp or Qwen2.5 32B Instruct better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 38.1 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.2-Exp does, with 164K tokens against 131K.

How many benchmarks do DeepSeek-V3.2-Exp and Qwen2.5 32B Instruct share?

4 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Qwen2.5 32B Instruct has 7.