Model comparison

Ministral 8B vs StarCoder 2 3B

Ministral 8B has enough public results to be ranked (#325); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Ministral 8B Mistral AI

28.2

Rank #325 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Side by side

Ministral 8B and StarCoder 2 3B specifications
Ministral 8BStarCoder 2 3B
ProviderMistral AINVIDIA
Noometry Index28.236.3
Released2024-10-012024-02-22
WeightsOpenOpen
Context window262K—
Max output262K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.15—
Results tracked177

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

Category by category

Coding Ministral 8B leads

Ministral 8B: 35.0 (#230), StarCoder 2 3B: 33.5

Coding benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Coding1202—
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Agentic & Tool Use Not comparable

Ministral 8B: 16.4 (#148), StarCoder 2 3B: —

Agentic & Tool Use benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
Berkeley Function Calling Leaderboard11.1%—

Reasoning Not comparable

Ministral 8B: 18.4 (#281), StarCoder 2 3B: —

Reasoning benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Hard Prompts1191—
DTBench45.7%—
Epoch Capabilities Index—88.76
WinoGrande—57.1%

Math Not comparable

Ministral 8B: 25.7 (#267), StarCoder 2 3B: —

Math benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Math1188—
MATH Level 514.9%—
GSM8K—21.6%

Knowledge Not comparable

Ministral 8B: 12.6 (#297), StarCoder 2 3B: —

Knowledge benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
GPQA Diamond27.1%—
Vectara Hallucination Rate7.4%—
LMArena Expert1170—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multilingual Not comparable

Ministral 8B: 35.1 (#247), StarCoder 2 3B: —

Multilingual benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Non-English1165—
LMArena Chinese1193—
LMArena Russian1195—

Instruction Following Not comparable

Ministral 8B: 60.5 (#250), StarCoder 2 3B: —

Instruction Following benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Instruction Following1161—

Long Context Not comparable

Ministral 8B: 36.7 (#227), StarCoder 2 3B: —

Long Context benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Longer Query1212—

Writing & Preference Not comparable

Ministral 8B: 39.6 (#246), StarCoder 2 3B: —

Writing & Preference benchmarks
BenchmarkMinistral 8BStarCoder 2 3B
LMArena Text1191—
LMArena Creative Writing1175—
LMArena Multi-Turn1166—

Frequently asked questions

Is Ministral 8B better than StarCoder 2 3B?

Ministral 8B has enough public results to be ranked (#325); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is Ministral 8B or StarCoder 2 3B better for coding?

Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.5 in the Noometry coding category.

How many benchmarks do Ministral 8B and StarCoder 2 3B share?

0 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper