Noometry

Model comparison

DeepSeek LLM 67B vs Mistral Large

Mistral Large is the stronger model overall, scoring 31.9 to 24.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Mistral Large Mistral AI

31.9

Rank #263 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Mistral Large in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Large leads 30.1 to 7.0.
  • The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 50.3% for Mistral Large.

Side by side

DeepSeek LLM 67BMistral Large
ProviderDeepSeekMistral AI
Noometry Index24.931.9
Released2023-11-292024-02-26
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1551

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

Category by category

Coding Mistral Large leads

DeepSeek LLM 67B: 31.9 (#278), Mistral Large: 34.3 (#240)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Coding10961277
SciCode—36.2%
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
ALE-Bench—264.7
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Mistral Large: 28.6 (#89)

BenchmarkDeepSeek LLM 67BMistral Large
Berkeley Function Calling Leaderboard—38.4%

Reasoning Too close to call

DeepSeek LLM 67B: 16.5 (#304), Mistral Large: 15.8 (#310)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Hard Prompts10701257
Epoch Capabilities Index110.5128.52
SimpleBench—22.5%
CritPt—0%
Chess Puzzles0%—
LiveBench Reasoning—43.5%
DTBench—65.1%
LiveBench Data Analysis—50.1%
LMCA—16.7%
ForecastBench—57.1
LiveBench—48.4%

Math Mistral Large leads

DeepSeek LLM 67B: 8.7 (#324), Mistral Large: 18.2 (#291)

BenchmarkDeepSeek LLM 67BMistral Large
OTIS Mock AIME 2024-20250.8%8.5%
LMArena Math11081262
MATH Level 56.4%50.3%
Omni-MATH—28.1%
LiveBench Math—42.5%
FrontierMath (Feb 2025 set)—0.3%

Knowledge Mistral Large leads

DeepSeek LLM 67B: 7.0 (#313), Mistral Large: 30.1 (#230)

BenchmarkDeepSeek LLM 67BMistral Large
GPQA Diamond24.6%51.3%
MMLU-Pro—59.9%
Confabulations—21.4%
Vectara Hallucination Rate—4.5%
GPQA (HELM)—43.5%
LMArena Expert—1232
MMLU—80%

Multilingual Mistral Large leads

DeepSeek LLM 67B: 29.4 (#267), Mistral Large: 40.0 (#219)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Non-English10731237
LMArena Chinese11321240
LMArena French—1325
LMArena German—1254
LMArena Japanese—1188
LMArena Korean—1202
LMArena Russian—1257
LMArena Spanish—1268

Instruction Following Mistral Large leads

DeepSeek LLM 67B: 55.4 (#277), Mistral Large: 67.9 (#191)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Instruction Following10791249
LiveBench Instruction Following—67.9%
IFEval—87.7%

Long Context Mistral Large leads

DeepSeek LLM 67B: 33.1 (#265), Mistral Large: 38.3 (#199)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Longer Query10921261

Writing & Preference Mistral Large leads

DeepSeek LLM 67B: 31.6 (#282), Mistral Large: 40.7 (#242)

BenchmarkDeepSeek LLM 67BMistral Large
LMArena Text11051266
LMArena Creative Writing10671243
LMArena Multi-Turn10821260
Short-Story Creative Writing—69%
EQ-Bench Creative Writing—985
WildBench—80.1%
LiveBench Language—39.4%

Frequently asked questions

Is DeepSeek LLM 67B better than Mistral Large?

Mistral Large is the stronger model overall, scoring 31.9 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Mistral Large better for coding?

Mistral Large scores higher on coding benchmarks: 34.3 versus 31.9 in the Noometry coding category.

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

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper