Model comparison

DeepSeek LLM 67B vs Mistral Nemo

Mistral Nemo is the stronger model overall, scoring 26.4 to 24.9 on the Noometry Index.

Last verified October 11, 2026. 3 shared benchmarks.

DeepSeek LLM 67B

DeepSeek

24.9

Rank #347 Confirmed

Mistral Nemo

Mistral AI

26.4

Rank #337 Confirmed

Summary

They share 3 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Mistral Nemo in 3 categories; 4 gaps are clear of the uncertainty.
The widest gap is in math, where Mistral Nemo leads 25.5 to 8.7.
The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 29.9% for Mistral Nemo.

Side by side

DeepSeek LLM 67B and Mistral Nemo specifications
	DeepSeek LLM 67B	Mistral Nemo
Provider	DeepSeek	Mistral AI
Noometry Index	24.9	26.4
Released	2023-11-29	2024-07-01
Weights	Open	Open
Context window	—	128K
Max output	—	128K
Input $ / M tokens	—	$0.15
Output $ / M tokens	—	$0.15
Results tracked	15	10

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

Category by category

Coding Not comparable

DeepSeek LLM 67B: 31.9 (#278), Mistral Nemo: —

Coding benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
LMArena Coding	1096	—

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Mistral Nemo: 23.5 (#125)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
Berkeley Function Calling Leaderboard	—	27.6%
BALROG	—	17.6%

Reasoning Mistral Nemo leads

DeepSeek LLM 67B: 16.5 (#304), Mistral Nemo: 20.7 (#232)

Reasoning benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
Epoch Capabilities Index	110.5	118.68
Chess Puzzles	0%	—
LMArena Hard Prompts	1070	—
DTBench	—	48.6%
PIQA	—	83.5%

Math Mistral Nemo leads

DeepSeek LLM 67B: 8.7 (#324), Mistral Nemo: 25.5 (#268)

Math benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
MATH Level 5	6.4%	10.8%
OTIS Mock AIME 2024-2025	0.8%	—
LMArena Math	1108	—
GSM8K	—	84.2%

Knowledge Mistral Nemo leads

DeepSeek LLM 67B: 7.0 (#313), Mistral Nemo: 12.3 (#298)

Knowledge benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
GPQA Diamond	24.6%	29.9%
BoolQ	—	82.5%

Multilingual Not comparable

DeepSeek LLM 67B: 29.4 (#267), Mistral Nemo: —

Multilingual benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
LMArena Non-English	1073	—
LMArena Chinese	1132	—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.4 (#277), Mistral Nemo: —

Instruction Following benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
LMArena Instruction Following	1079	—

Long Context Not comparable

DeepSeek LLM 67B: 33.1 (#265), Mistral Nemo: —

Long Context benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
LMArena Longer Query	1092	—

Writing & Preference DeepSeek LLM 67B leads

DeepSeek LLM 67B: 31.6 (#282), Mistral Nemo: 28.5 (#296)

Writing & Preference benchmarks
Benchmark	DeepSeek LLM 67B	Mistral Nemo
LMArena Text	1105	—
LMArena Creative Writing	1067	—
EQ-Bench Creative Writing	—	881
LMArena Multi-Turn	1082	—

Frequently asked questions

Is DeepSeek LLM 67B better than Mistral Nemo?