Noometry

Model comparison

Deepseek Coder v2 vs Mistral Small

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index.

Last verified . 19 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Mistral Small Mistral AI

33.4

Rank #243 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and Mistral Small in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 16.4.
  • The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 46.6% for Mistral Small.

Side by side

Deepseek Coder v2Mistral Small
ProviderDeepSeekMistral AI
Noometry Index35.933.4
Released2024-06-172024-02-26
WeightsOpenOpen
Context window—262K
Max output—256K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.60
Results tracked2439

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

Category by category

Coding Deepseek Coder v2 leads

Deepseek Coder v2: 38.1 (#183), Mistral Small: 34.0 (#247)

BenchmarkDeepseek Coder v2Mistral Small
BigCodeBench Instruct48.2%36.1%
LMArena Coding12511362
BigCodeBench Complete59.7%46.6%
SciCode—26.5%
LiveBench Coding—36.2%
ALE-Bench—497.62
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, Mistral Small: 28.1 (#93)

BenchmarkDeepseek Coder v2Mistral Small
Berkeley Function Calling Leaderboard—37.1%

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), Mistral Small: 19.8 (#250)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Hard Prompts12071335
Kagi LLM Benchmark—37.8%
CritPt—0%
LiveBench Reasoning—44.8%
DTBench—70.9%
LiveBench Data Analysis—53.7%
LMCA—20.6%
LiveBench—44%
WinoGrande83.7%—

Math Deepseek Coder v2 leads

Deepseek Coder v2: 34.9 (#190), Mistral Small: 16.4 (#293)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Math12411341
OTIS Mock AIME 2024-2025—5.8%
LiveBench Math—39.9%
MATH Level 5—46.8%
GSM8K94.5%—

Knowledge Deepseek Coder v2 leads

Deepseek Coder v2: 32.3 (#212), Mistral Small: 31.0 (#222)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Expert11811291
GPQA Diamond—47.5%
Vectara Hallucination Rate—5.1%
ARC (AI2) Challenge64.3%—
MMLU—68.7%

Multimodal Not comparable

Deepseek Coder v2: —, Mistral Small: 33.5 (#96)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Vision—1142

Multilingual Mistral Small leads

Deepseek Coder v2: 36.3 (#240), Mistral Small: 45.5 (#169)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Non-English11821315
LMArena Chinese12011340
LMArena French11851337
LMArena German11641340
LMArena Japanese11261275
LMArena Korean11041259
LMArena Russian11881324
LMArena Spanish11531346

Instruction Following Mistral Small leads

Deepseek Coder v2: 61.7 (#242), Mistral Small: 66.4 (#209)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Instruction Following11801310
LiveBench Instruction Following—63.7%

Long Context Mistral Small leads

Deepseek Coder v2: 37.0 (#224), Mistral Small: 40.4 (#156)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Longer Query12191327

Writing & Preference Mistral Small leads

Deepseek Coder v2: 38.2 (#253), Mistral Small: 52.5 (#171)

BenchmarkDeepseek Coder v2Mistral Small
LMArena Text11911338
LMArena Creative Writing11201305
LMArena Multi-Turn11771344
LiveBench Language—30.5%

Frequently asked questions

Is Deepseek Coder v2 better than Mistral Small?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index.

Is Deepseek Coder v2 or Mistral Small better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.0 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Mistral Small share?

19 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Small has 39.

Related comparisons

Go deeper