Model comparison

Phi 3 Small 8k Instruct vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.3 on the Noometry Index.

Last verified . 13 shared benchmarks.

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 31.1.
  • Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

Side by side

Phi 3 Small 8k Instruct and Step 5 Preview specifications
Phi 3 Small 8k InstructStep 5 Preview
ProviderMicrosoftStepFun
Noometry Index29.347.9
Released2024-04-232026-09-16
WeightsOpenProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked3218

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

Category by category

Coding Step 5 Preview leads

Phi 3 Small 8k Instruct: 27.9 (#318), Step 5 Preview: 51.8 (#36)

Coding benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Coding11011480
LMArena WebDev—1564
SciCode—58.9%
LiveBench Coding20.3%—

Reasoning Step 5 Preview leads

Phi 3 Small 8k Instruct: 14.8 (#323), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Hard Prompts11001465
CritPt—20.9%
LiveBench Reasoning15.9%—
LiveBench Data Analysis30.3%—
Adversarial NLI58.1%—
BIG-Bench Hard79.1%—
HellaSwag77%—
LiveBench24%—
WinoGrande81.5%—

Math Step 5 Preview leads

Phi 3 Small 8k Instruct: 27.6 (#248), Step 5 Preview: 46.1 (#72)

Math benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Math11511470
ProofBench—42%
LiveBench Math17.6%—

Knowledge Step 5 Preview leads

Phi 3 Small 8k Instruct: 29.1 (#240), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Expert10671470
ARC (AI2) Challenge90.7%—
MMLU75.7%—
OpenBookQA88%—
TriviaQA58.1%—

Multimodal Not comparable

Phi 3 Small 8k Instruct: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

Phi 3 Small 8k Instruct: 28.5 (#272), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Non-English10581432
LMArena Chinese10611519
LMArena Russian11111436
LMArena Spanish11111439
LMArena French1135—
LMArena German1080—
LMArena Japanese966—
LMArena Korean894—

Instruction Following Step 5 Preview leads

Phi 3 Small 8k Instruct: 51.9 (#292), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Instruction Following10871444
LiveBench Instruction Following47.2%—

Long Context Step 5 Preview leads

Phi 3 Small 8k Instruct: 33.0 (#267), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Longer Query10881455

Writing & Preference Step 5 Preview leads

Phi 3 Small 8k Instruct: 31.1 (#284), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
BenchmarkPhi 3 Small 8k InstructStep 5 Preview
LMArena Text11101442
LMArena Creative Writing10831410
LMArena Multi-Turn10681447
LiveBench Language12.9%—

Frequently asked questions

Is Phi 3 Small 8k Instruct better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.3 on the Noometry Index.

Is Phi 3 Small 8k Instruct or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 27.9 in the Noometry coding category.

How many benchmarks do Phi 3 Small 8k Instruct and Step 5 Preview share?

13 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper