Model comparison

DeepSeek-V3.1 vs Qwen3-1.7B

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 26.2 on the Noometry Index.

Last verified October 10, 2026. 0 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.2

Rank #106 Confirmed

Qwen3-1.7B

Alibaba (Qwen)

26.2

Rank #331 Reported

Summary

The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 19.6.

Side by side

DeepSeek-V3.1 and Qwen3-1.7B specifications
	DeepSeek-V3.1	Qwen3-1.7B
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	42.2	26.2
Released	2025-08-21	2025-04-29
Weights	Open	Open
Context window	164K	—
Max output	8K	—
Input $ / M tokens	$0.25	—
Output $ / M tokens	$0.95	—
Results tracked	27	4

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

Category by category

Coding Not comparable

DeepSeek-V3.1: 39.8 (#140), Qwen3-1.7B: —

Coding benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
WeirdML	38.4%	—
LMArena Coding	1417	—

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Qwen3-1.7B: 24.5 (#108)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
Berkeley Function Calling Leaderboard	—	28.4%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), Qwen3-1.7B: 18.5 (#263)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
SimpleBench	40%	—
Kagi LLM Benchmark	53.2%	—
Chess Puzzles	—	0%
LMArena Hard Prompts	1417	—
DTBench	82.7%	—
LMCA	24.3%	—
Epoch Capabilities Index	139.92	—
ForecastBench	58	—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Qwen3-1.7B: 15.4 (#288)

Math benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
OTIS Mock AIME 2024-2025	—	8.1%
LMArena Math	1420	—

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), Qwen3-1.7B: 19.6 (#273)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
GPQA Diamond	—	38%
Vectara Hallucination Rate	5.5%	—
LMArena Expert	1403	—

Multilingual Not comparable

DeepSeek-V3.1: 51.8 (#100), Qwen3-1.7B: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
LMArena Non-English	1400	—
LMArena Chinese	1470	—
LMArena French	1447	—
LMArena German	1412	—
LMArena Japanese	1374	—
LMArena Korean	1337	—
LMArena Russian	1405	—
LMArena Spanish	1429	—

Instruction Following Not comparable

DeepSeek-V3.1: 74.1 (#105), Qwen3-1.7B: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
LMArena Instruction Following	1400	—

Long Context Not comparable

DeepSeek-V3.1: 36.3 (#227), Qwen3-1.7B: —

Long Context benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
Fiction.LiveBench	52.8%	—
LMArena Longer Query	1422	—

Writing & Preference Not comparable

DeepSeek-V3.1: 60.5 (#93), Qwen3-1.7B: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	Qwen3-1.7B
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 Qwen3-1.7B?