Model comparison

DeepSeek LLM 67B vs Qwen2.5-VL 72B Instruct

Qwen2.5-VL 72B Instruct is the stronger model overall, scoring 29.9 to 24.9 on the Noometry Index.

Last verified October 12, 2026. 0 shared benchmarks.

DeepSeek LLM 67B

DeepSeek

24.9

Rank #347 Confirmed

Qwen2.5-VL 72B Instruct

Alibaba (Qwen)

29.9

Rank #302 Confirmed

Summary

The widest gap is in reasoning, where Qwen2.5-VL 72B Instruct leads 20.7 to 16.5.

Side by side

DeepSeek LLM 67B and Qwen2.5-VL 72B Instruct specifications
	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
Provider	DeepSeek	Alibaba (Qwen)
Noometry Index	24.9	29.9
Released	2023-11-29	2024-09
Weights	Open	Open
Context window	—	131K
Max output	—	8K
Input $ / M tokens	—	$2.80
Output $ / M tokens	—	$8.40
Results tracked	15	6

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

Category by category

Coding Not comparable

DeepSeek LLM 67B: 31.9 (#278), Qwen2.5-VL 72B Instruct: —

Coding benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Coding	1096	—

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Qwen2.5-VL 72B Instruct: 18.6 (#144)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
OSWorld	—	5%

Reasoning Qwen2.5-VL 72B Instruct leads

DeepSeek LLM 67B: 16.5 (#304), Qwen2.5-VL 72B Instruct: 20.7 (#233)

Reasoning benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
Kagi LLM Benchmark	—	36%
Chess Puzzles	0%	—
LMArena Hard Prompts	1070	—
Epoch Capabilities Index	110.5	—

Math Not comparable

DeepSeek LLM 67B: 8.7 (#324), Qwen2.5-VL 72B Instruct: —

Math benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
OTIS Mock AIME 2024-2025	0.8%	—
LMArena Math	1108	—
MATH Level 5	6.4%	—

Knowledge Not comparable

DeepSeek LLM 67B: 7.0 (#313), Qwen2.5-VL 72B Instruct: —

Knowledge benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
GPQA Diamond	24.6%	—

Multimodal Not comparable

DeepSeek LLM 67B: —, Qwen2.5-VL 72B Instruct: 33.5 (#97)

Multimodal benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Vision	—	1107
Video-MME	—	73.5%
GeoBench	—	62%
SpatialViz-Bench	—	33.3%

Multilingual Not comparable

DeepSeek LLM 67B: 29.4 (#267), Qwen2.5-VL 72B Instruct: —

Multilingual benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Non-English	1073	—
LMArena Chinese	1132	—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.4 (#277), Qwen2.5-VL 72B Instruct: —

Instruction Following benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Instruction Following	1079	—

Long Context Not comparable

DeepSeek LLM 67B: 33.1 (#265), Qwen2.5-VL 72B Instruct: —

Long Context benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Longer Query	1092	—

Writing & Preference Not comparable

DeepSeek LLM 67B: 31.6 (#282), Qwen2.5-VL 72B Instruct: —

Writing & Preference benchmarks
Benchmark	DeepSeek LLM 67B	Qwen2.5-VL 72B Instruct
LMArena Text	1105	—
LMArena Creative Writing	1067	—
LMArena Multi-Turn	1082	—

Frequently asked questions

Is DeepSeek LLM 67B better than Qwen2.5-VL 72B Instruct?