Model comparison

Ministral 3B vs Phi 3 Mini 4k Instruct June 2024

Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 25.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

Ministral 3B Mistral AI

25.6

Rank #336 Confirmed

Summary

  • The widest gap is in knowledge, where Phi 3 Mini 4k Instruct June 2024 leads 28.1 to 10.4.

Side by side

Ministral 3B and Phi 3 Mini 4k Instruct June 2024 specifications
Ministral 3BPhi 3 Mini 4k Instruct June 2024
ProviderMistral AIMicrosoft
Noometry Index25.630.7
Released2024-10-01—
WeightsOpenOpen
Context window128K—
Max output128K—
Input $ / M tokens$0.04—
Output $ / M tokens$0.04—
Results tracked615

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

Category by category

Coding Not comparable

Ministral 3B: —, Phi 3 Mini 4k Instruct June 2024: 31.2 (#275)

Coding benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Coding—1093

Reasoning Phi 3 Mini 4k Instruct June 2024 leads

Ministral 3B: 17.7 (#278), Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)

Reasoning benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Hard Prompts—1088
DTBench51.7%—
LMCA5.5%—
Epoch Capabilities Index118.08—

Math Phi 3 Mini 4k Instruct June 2024 leads

Ministral 3B: 24.5 (#257), Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)

Math benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Math—1152
MATH Level 514.4%—

Knowledge Phi 3 Mini 4k Instruct June 2024 leads

Ministral 3B: 10.4 (#297), Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)

Knowledge benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
GPQA Diamond25.3%—
Vectara Hallucination Rate7.3%—
LMArena Expert—1051

Multilingual Not comparable

Ministral 3B: —, Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)

Multilingual benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Non-English—1013
LMArena Chinese—1033
LMArena German—1031
LMArena Japanese—954
LMArena Korean—880
LMArena Russian—1019

Instruction Following Not comparable

Ministral 3B: —, Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)

Instruction Following benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Instruction Following—1058

Long Context Not comparable

Ministral 3B: —, Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)

Long Context benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Longer Query—1042

Writing & Preference Not comparable

Ministral 3B: —, Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)

Writing & Preference benchmarks
BenchmarkMinistral 3BPhi 3 Mini 4k Instruct June 2024
LMArena Text—1080
LMArena Creative Writing—1045
LMArena Multi-Turn—1049

Frequently asked questions

Is Ministral 3B better than Phi 3 Mini 4k Instruct June 2024?

Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 25.6 on the Noometry Index.

How many benchmarks do Ministral 3B and Phi 3 Mini 4k Instruct June 2024 share?

0 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.

Related comparisons

Go deeper