Model comparison

DeepSeek LLM 67B vs Qwen3.5 Plus

Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 24.8 on the Noometry Index.

Last verified October 10, 2026. 4 shared benchmarks.

DeepSeek LLM 67B

DeepSeek

24.8

Rank #341 Confirmed

Qwen3.5 Plus

Alibaba (Qwen)

42.3

Rank #103 Confirmed

Summary

They share 4 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen3.5 Plus in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where Qwen3.5 Plus leads 47.9 to 8.1.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 86.7% for Qwen3.5 Plus.
DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67B and Qwen3.5 Plus specifications
	DeepSeek LLM 67B	Qwen3.5 Plus
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	24.8	42.3
Released	2023-11-29	2026-02-16
Weights	Open	Proprietary
Context window	—	1M
Max output	—	66K
Input $ / M tokens	—	$0.40
Output $ / M tokens	—	$2.40
Results tracked	15	15

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

Category by category

Coding Not comparable

DeepSeek LLM 67B: 31.3 (#273), Qwen3.5 Plus: —

Coding benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
LMArena Coding	1096	—
ALE-Bench	—	621.92

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Qwen3.5 Plus: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
Vending-Bench 2	—	0.54

Reasoning Qwen3.5 Plus leads

DeepSeek LLM 67B: 15.9 (#300), Qwen3.5 Plus: 32.0 (#67)

Reasoning benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
Chess Puzzles	0%	22%
Epoch Capabilities Index	110.54	146.79
LMArena Hard Prompts	1070	—
Mystery Game Puzzles	—	17%
DTBench	—	80.5%
LMCA	—	36.4%

Math Qwen3.5 Plus leads

DeepSeek LLM 67B: 8.1 (#318), Qwen3.5 Plus: 47.9 (#55)

Math benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
OTIS Mock AIME 2024-2025	0.8%	86.7%
LMArena Math	1108	—
MATH Level 5	6.4%	—
FrontierMath (Feb 2025 set)	—	21%
FrontierMath Tier 4 (v1)	—	2.1%

Knowledge Qwen3.5 Plus leads

DeepSeek LLM 67B: 7.1 (#308), Qwen3.5 Plus: 46.0 (#78)

Knowledge benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
GPQA Diamond	24.6%	84.8%
SimpleQA Verified	—	25.4%
Vectara Hallucination Rate	—	10.7%

Multilingual Not comparable

DeepSeek LLM 67B: 29.5 (#262), Qwen3.5 Plus: —

Multilingual benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
LMArena Non-English	1073	—
LMArena Chinese	1132	—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.7 (#272), Qwen3.5 Plus: —

Instruction Following benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
LMArena Instruction Following	1079	—

Long Context Qwen3.5 Plus leads

DeepSeek LLM 67B: 33.1 (#260), Qwen3.5 Plus: 42.9 (#109)

Long Context benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
CL-bench	—	19.8%
CL-bench Life	—	12.4%
LMArena Longer Query	1092	—

Writing & Preference Not comparable

DeepSeek LLM 67B: 31.8 (#277), Qwen3.5 Plus: —

Writing & Preference benchmarks
Benchmark	DeepSeek LLM 67B	Qwen3.5 Plus
LMArena Text	1105	—
LMArena Creative Writing	1067	—
LMArena Multi-Turn	1082	—

Frequently asked questions

Is DeepSeek LLM 67B better than Qwen3.5 Plus?