Model comparison

DeepSeek V4.1 Flash vs Qwen3-30B-A3B

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.9 on the Noometry Index.

Last verified October 10, 2026. 24 shared benchmarks.

DeepSeek V4.1 Flash

DeepSeek

52.8

Rank #38 Confirmed

Qwen3-30B-A3B

Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

They share 24 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and Qwen3-30B-A3B in 0 categories; 9 gaps are clear of the uncertainty.
The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 37.4.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 70.3% for Qwen3-30B-A3B.
Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
DeepSeek V4.1 Flash accepts more context: 1M tokens versus 41K.

Side by side

DeepSeek V4.1 Flash and Qwen3-30B-A3B specifications
	DeepSeek V4.1 Flash	Qwen3-30B-A3B
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	52.8	38.9
Released	2026-09-09	2025-04-28
Weights	Open	Open
Context window	1M	41K
Max output	393K	16K
Input $ / M tokens	$0.15	$0.12
Output $ / M tokens	$0.60	$0.50
Results tracked	37	32

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Qwen3-30B-A3B: 37.5 (#194)

Coding benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
SciCode	51.9%	33.3%
LMArena Coding	1506	1416
LMArena WebDev	1619	—
WeirdML	—	29.8%
ALE-Bench	1,092	—

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), Qwen3-30B-A3B: 29.8 (#82)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
APEX-Agents	39.5%	—
Berkeley Function Calling Leaderboard	—	41.4%
GDP.pdf	19.8%	—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Qwen3-30B-A3B: 22.2 (#204)

Reasoning benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
CritPt	14.3%	0.3%
LMArena Hard Prompts	1483	1398
DTBench	89.9%	69.3%
LMCA	47%	22.4%
Epoch Capabilities Index	154.9	139.63
Kagi LLM Benchmark	—	54.9%
NYT Connections (extended)	89.6%	—
Chess Puzzles	—	8%
Mystery Game Puzzles	43%	—
Surface Evolver Bench	46.3%	—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Qwen3-30B-A3B: 37.4 (#157)

Math benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
OTIS Mock AIME 2024-2025	98.3%	70.3%
LMArena Math	1477	1394
FrontierMath (Tiers 1-3)	67.4%	—
FrontierMath Tier 4	26.8%	—
MathArena Final-Answer Competitions	—	47.8%
ProofBench	54%	—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Qwen3-30B-A3B: 41.8 (#105)

Knowledge benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
GPQA Diamond	89.8%	70.1%
LMArena Expert	1506	1396
Confabulations	—	12.3%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Qwen3-30B-A3B: —

Multimodal benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
LMArena Vision	1277	—
Furniture Assembly	34.2%	—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Qwen3-30B-A3B: 49.5 (#132)

Multilingual benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
LMArena Non-English	1448	1372
LMArena Chinese	1497	1433
LMArena French	1452	1418
LMArena German	1484	1380
LMArena Japanese	1412	1337
LMArena Korean	1452	1331
LMArena Russian	1471	1370
LMArena Spanish	1459	1404

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Qwen3-30B-A3B: 72.0 (#142)

Instruction Following benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
LMArena Instruction Following	1474	1363

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Qwen3-30B-A3B: 31.0 (#283)

Long Context benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
LMArena Longer Query	1475	1379
Fiction.LiveBench	—	40.6%

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Qwen3-30B-A3B: 55.6 (#143)

Writing & Preference benchmarks
Benchmark	DeepSeek V4.1 Flash	Qwen3-30B-A3B
LMArena Text	1462	1384
LMArena Creative Writing	1435	1317
LMArena Multi-Turn	1457	1378
Short-Story Creative Writing	—	75.3%
EQ-Bench Creative Writing	1540	—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Qwen3-30B-A3B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.9 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.

Is DeepSeek V4.1 Flash or Qwen3-30B-A3B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 41K.

How many benchmarks do DeepSeek V4.1 Flash and Qwen3-30B-A3B share?

24 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen3-30B-A3B has 32.