Model comparison

DeepSeek V4 Pro vs Qwen3.6 35B-A3B

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.2 on the Noometry Index.

Last verified October 10, 2026. 13 shared benchmarks.

DeepSeek V4 Pro

DeepSeek

54.2

Rank #28 Confirmed

Qwen3.6 35B-A3B

Alibaba (Qwen)

37.2

Rank #194 Confirmed

Summary

They share 13 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Qwen3.6 35B-A3B in 0 categories; 5 gaps are clear of the uncertainty.
The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.4 to 27.2.
The biggest single-benchmark swing is NYT Connections (extended): 91.3% for DeepSeek V4 Pro and 41.6% for Qwen3.6 35B-A3B.
Both cost about the same: $0.43 input and $0.87 output per million tokens.
DeepSeek V4 Pro accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4 Pro and Qwen3.6 35B-A3B specifications
	DeepSeek V4 Pro	Qwen3.6 35B-A3B
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	54.2	37.2
Released	2026-04-24	2026-04-01
Weights	Open	Open
Context window	1M	262K
Max output	393K	66K
Input $ / M tokens	$0.43	$0.25
Output $ / M tokens	$0.87	$1.49
Results tracked	48	14

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

Category by category

Coding DeepSeek V4 Pro leads

DeepSeek V4 Pro: 52.2 (#31), Qwen3.6 35B-A3B: 36.7 (#190)

Coding benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
SciCode	51%	35.8%
WeirdML	66.2%	34.5%
SWE-bench Verified	77.6%	—
FrontierCode	28.6%	—
LMArena WebDev	1582	—
LMArena Coding	1470	—
ALE-Bench	1,403	—

Agentic & Tool Use DeepSeek V4 Pro leads

DeepSeek V4 Pro: 32.7 (#54), Qwen3.6 35B-A3B: 21.9 (#126)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
Terminal-Bench	—	23%
APEX-Agents	47.3%	—
Vending-Bench 2	3,285	—

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.4 (#22), Qwen3.6 35B-A3B: 27.2 (#112)

Reasoning benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
NYT Connections (extended)	91.3%	41.6%
CritPt	18%	0.3%
Chess Puzzles	47%	26%
Mystery Game Puzzles	43%	22%
DTBench	93.9%	73.9%
LMCA	45.5%	29.7%
Surface Evolver Bench	40%	44.4%
Epoch Capabilities Index	155.39	143.92
ARC-AGI-2	61.3%	—
Kagi LLM Benchmark	53.5%	—
ARC-AGI-1	90.5%	—
LMArena Hard Prompts	1461	—
ForecastBench	56.1	—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.6 (#24), Qwen3.6 35B-A3B: 37.9 (#90)

Math benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
FrontierMath (Tiers 1-3)	64.6%	20.4%
OTIS Mock AIME 2024-2025	98.6%	86.7%
FrontierMath Tier 4	26.8%	—
MathArena Final-Answer Competitions	76.6%	—
ProofBench	50%	—
LMArena Math	1455	—

Knowledge DeepSeek V4 Pro leads

DeepSeek V4 Pro: 59.5 (#28), Qwen3.6 35B-A3B: 51.4 (#63)

Knowledge benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
GPQA Diamond	91.7%	84.8%
SimpleQA Verified	52.9%	—
Vectara Hallucination Rate	8.6%	—
LMArena Expert	1463	—

Multilingual Not comparable

DeepSeek V4 Pro: 54.5 (#44), Qwen3.6 35B-A3B: —

Multilingual benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
LMArena Non-English	1438	—
LMArena Chinese	1486	—
LMArena French	1473	—
LMArena German	1458	—
LMArena Japanese	1448	—
LMArena Korean	1452	—
LMArena Russian	1452	—
LMArena Spanish	1457	—

Instruction Following Not comparable

DeepSeek V4 Pro: 76.3 (#44), Qwen3.6 35B-A3B: —

Instruction Following benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
LMArena Instruction Following	1448	—

Long Context Not comparable

DeepSeek V4 Pro: 45.0 (#49), Qwen3.6 35B-A3B: —

Long Context benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
CL-bench Life	13.5%	—
LMArena Longer Query	1459	—

Writing & Preference Not comparable

DeepSeek V4 Pro: 65.6 (#45), Qwen3.6 35B-A3B: —

Writing & Preference benchmarks
Benchmark	DeepSeek V4 Pro	Qwen3.6 35B-A3B
LMArena Text	1451	—
LMArena Creative Writing	1446	—
EQ-Bench Creative Writing	1553	—
EQ-Bench 4	1166	—
LMArena Multi-Turn	1467	—

Frequently asked questions

Is DeepSeek V4 Pro better than Qwen3.6 35B-A3B?

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 37.2 on the Noometry Index.

Which is cheaper, DeepSeek V4 Pro or Qwen3.6 35B-A3B?

DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.

Is DeepSeek V4 Pro or Qwen3.6 35B-A3B better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 36.7 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 262K.

How many benchmarks do DeepSeek V4 Pro and Qwen3.6 35B-A3B share?

13 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen3.6 35B-A3B has 14.