Noometry

Model comparison

Phi 3 Mini 128k Instruct vs Pixtral Large

Pixtral Large is the stronger model overall, scoring 32.2 to 29.7 on the Noometry Index.

Last verified . 0 shared benchmarks.

Phi 3 Mini 128k Instruct Microsoft

29.7

Rank #305 Confirmed

Pixtral Large Mistral AI

32.2

Rank #259 Reported

Summary

  • The widest gap is in writing & preference, where Pixtral Large leads 32.9 to 27.1.

Side by side

Phi 3 Mini 128k InstructPixtral Large
ProviderMicrosoftMistral AI
Noometry Index29.732.2
Released2024-04-232024-11-01
WeightsOpenOpen
Context window—128K
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked193

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

Category by category

Coding Not comparable

Phi 3 Mini 128k Instruct: 28.8 (#312), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
BigCodeBench Instruct29.6%—
LMArena Coding1039—
BigCodeBench Complete40.6%—

Reasoning Pixtral Large leads

Phi 3 Mini 128k Instruct: 19.6 (#256), Pixtral Large: 21.7 (#218)

BenchmarkPhi 3 Mini 128k InstructPixtral Large
EnigmaEval—0.8%
LMArena Hard Prompts1028—

Math Not comparable

Phi 3 Mini 128k Instruct: 31.6 (#222), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Math1089—

Knowledge Not comparable

Phi 3 Mini 128k Instruct: 26.8 (#254), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Expert984—

Multimodal Not comparable

Phi 3 Mini 128k Instruct: —, Pixtral Large: 30.6 (#111)

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Vision—1089

Multilingual Not comparable

Phi 3 Mini 128k Instruct: 25.2 (#285), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Non-English1000—
LMArena Chinese1016—
LMArena French1039—
LMArena German1006—
LMArena Japanese899—
LMArena Korean856—
LMArena Russian1004—
LMArena Spanish1059—

Instruction Following Not comparable

Phi 3 Mini 128k Instruct: 51.8 (#294), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Instruction Following1023—

Long Context Not comparable

Phi 3 Mini 128k Instruct: 30.4 (#289), Pixtral Large: —

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Longer Query996—

Writing & Preference Pixtral Large leads

Phi 3 Mini 128k Instruct: 27.1 (#301), Pixtral Large: 32.9 (#278)

BenchmarkPhi 3 Mini 128k InstructPixtral Large
LMArena Text1050—
LMArena Creative Writing1024—
EQ-Bench Creative Writing—988
LMArena Multi-Turn989—

Frequently asked questions

Is Phi 3 Mini 128k Instruct better than Pixtral Large?

Pixtral Large is the stronger model overall, scoring 32.2 to 29.7 on the Noometry Index.

How many benchmarks do Phi 3 Mini 128k Instruct and Pixtral Large share?

0 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Pixtral Large has 3.

Related comparisons

Go deeper