Noometry

Model comparison

DeepSeek LLM 67B vs Mistral Small 3

Mistral Small 3 is the stronger model overall, scoring 30.9 to 24.8 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.8

Rank #341 Confirmed

Mistral Small 3 Mistral AI

30.9

Rank #268 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mistral Small 3 in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small 3 leads 25.0 to 7.1.
  • The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 47.3% for Mistral Small 3.

Side by side

DeepSeek LLM 67BMistral Small 3
ProviderDeepSeekMistral AI
Noometry Index24.830.9
Released2023-11-292025-01-30
WeightsOpenOpen
Context window—33K
Max output—16K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.08
Results tracked1524

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

Category by category

Coding Mistral Small 3 leads

DeepSeek LLM 67B: 31.3 (#273), Mistral Small 3: 36.0 (#203)

BenchmarkDeepSeek LLM 67BMistral Small 3
LMArena Coding10961246
BigCodeBench Instruct—45.3%
BigCodeBench Complete—50.4%

Reasoning Mistral Small 3 leads

DeepSeek LLM 67B: 15.9 (#300), Mistral Small 3: 18.2 (#269)

BenchmarkDeepSeek LLM 67BMistral Small 3
Chess Puzzles0%0%
LMArena Hard Prompts10701233
Epoch Capabilities Index110.54127.06

Math Mistral Small 3 leads

DeepSeek LLM 67B: 8.1 (#318), Mistral Small 3: 15.3 (#290)

BenchmarkDeepSeek LLM 67BMistral Small 3
OTIS Mock AIME 2024-20250.8%6.7%
LMArena Math11081240
MATH Level 56.4%—

Knowledge Mistral Small 3 leads

DeepSeek LLM 67B: 7.1 (#308), Mistral Small 3: 25.0 (#258)

BenchmarkDeepSeek LLM 67BMistral Small 3
GPQA Diamond24.6%47.3%
Confabulations—25.2%
LMArena Expert—1202

Multilingual Mistral Small 3 leads

DeepSeek LLM 67B: 29.5 (#262), Mistral Small 3: 37.5 (#231)

BenchmarkDeepSeek LLM 67BMistral Small 3
LMArena Non-English10731198
LMArena Chinese11321204
LMArena French—1202
LMArena German—1211
LMArena Japanese—1111
LMArena Korean—1188
LMArena Russian—1216

Instruction Following Mistral Small 3 leads

DeepSeek LLM 67B: 55.7 (#272), Mistral Small 3: 63.9 (#224)

BenchmarkDeepSeek LLM 67BMistral Small 3
LMArena Instruction Following10791214

Long Context Mistral Small 3 leads

DeepSeek LLM 67B: 33.1 (#260), Mistral Small 3: 37.8 (#206)

BenchmarkDeepSeek LLM 67BMistral Small 3
LMArena Longer Query10921246

Writing & Preference Too close to call

DeepSeek LLM 67B: 31.8 (#277), Mistral Small 3: 32.4 (#275)

BenchmarkDeepSeek LLM 67BMistral Small 3
LMArena Text11051234
LMArena Creative Writing10671195
LMArena Multi-Turn10821217
EQ-Bench Creative Writing—707

Frequently asked questions

Is DeepSeek LLM 67B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 30.9 to 24.8 on the Noometry Index.

Is DeepSeek LLM 67B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 31.3 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Mistral Small 3 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Small 3 has 24.

Related comparisons

Go deeper