Model comparison

DeepSeek-V3.1 vs Qwen3 14B

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 35.5 on the Noometry Index.

Last verified October 11, 2026. 6 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.8

Rank #108 Confirmed

Qwen3 14B

Alibaba (Qwen)

35.5

Rank #225 Confirmed

Summary

They share 6 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 4 categories and Qwen3 14B in 1 category; 4 gaps are clear of the uncertainty.
The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 18.5.
The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 64% for Qwen3 14B.
DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
DeepSeek-V3.1 accepts more context: 164K tokens versus 131K.

Side by side

DeepSeek-V3.1 and Qwen3 14B specifications
	DeepSeek-V3.1	Qwen3 14B
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	42.8	35.5
Released	2025-08-21	2025-04
Weights	Open	Open
Context window	164K	131K
Max output	8K	8K
Input $ / M tokens	$0.25	$0.35
Output $ / M tokens	$0.95	$1.40
Results tracked	27	12

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 40.3 (#144), Qwen3 14B: 37.3 (#195)

Coding benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
SciCode	—	31.6%
WeirdML	38.4%	—
LMArena Coding	1417	—

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Qwen3 14B: 29.6 (#83)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
Berkeley Function Calling Leaderboard	—	41%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), Qwen3 14B: 18.5 (#280)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
Kagi LLM Benchmark	53.2%	49.1%
DTBench	82.7%	64%
LMCA	24.3%	18.2%
Epoch Capabilities Index	139.92	138.23
SimpleBench	40%	—
CritPt	—	0%
Chess Puzzles	—	4%
LMArena Hard Prompts	1417	—
ForecastBench	58	—

Math Too close to call

DeepSeek-V3.1: 38.9 (#122), Qwen3 14B: 38.6 (#133)

Math benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
OTIS Mock AIME 2024-2025	—	66.4%
LMArena Math	1420	—

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), Qwen3 14B: 39.3 (#134)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
Vectara Hallucination Rate	5.5%	5.4%
GPQA Diamond	—	63.8%
LMArena Expert	1405	—

Multilingual Not comparable

DeepSeek-V3.1: 51.6 (#106), Qwen3 14B: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
LMArena Non-English	1400	—
LMArena Chinese	1469	—
LMArena French	1447	—
LMArena German	1411	—
LMArena Japanese	1378	—
LMArena Korean	1337	—
LMArena Russian	1405	—
LMArena Spanish	1431	—

Instruction Following Not comparable

DeepSeek-V3.1: 73.9 (#110), Qwen3 14B: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
LMArena Instruction Following	1400	—

Long Context Qwen3 14B leads

DeepSeek-V3.1: 36.3 (#232), Qwen3 14B: 38.1 (#204)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
Fiction.LiveBench	52.8%	62.5%
LMArena Longer Query	1422	—

Writing & Preference Not comparable

DeepSeek-V3.1: 60.3 (#98), Qwen3 14B: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	Qwen3 14B
LMArena Text	1420	—
LMArena Creative Writing	1401	—
EQ-Bench Creative Writing	1436	—
LMArena Multi-Turn	1408	—

Frequently asked questions

Is DeepSeek-V3.1 better than Qwen3 14B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 35.5 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or Qwen3 14B?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

Is DeepSeek-V3.1 or Qwen3 14B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 131K.

How many benchmarks do DeepSeek-V3.1 and Qwen3 14B share?

6 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3 14B has 12.