Noometry

Model comparison

Granite 4.0 H Small vs Phi 3 Mini 4k Instruct

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 47.7.

Side by side

Granite 4.0 H SmallPhi 3 Mini 4k Instruct
ProviderIBMMicrosoft
Noometry Index36.527.9
Released—2024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1935

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

Category by category

Coding Granite 4.0 H Small leads

Granite 4.0 H Small: 36.4 (#209), Phi 3 Mini 4k Instruct: 26.6 (#323)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Coding12491093
LiveBench Coding—15.5%
HumanEval+—59.1%
MBPP+—54.2%

Reasoning Granite 4.0 H Small leads

Granite 4.0 H Small: 24.4 (#163), Phi 3 Mini 4k Instruct: 14.1 (#328)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Hard Prompts12401072
Chess Puzzles—0%
LiveBench Reasoning—26.8%
LiveBench Data Analysis—34.7%
Adversarial NLI—52.8%
BIG-Bench Hard—71.7%
HellaSwag—76.7%
LiveBench—22.4%
WinoGrande—70.8%

Math Granite 4.0 H Small leads

Granite 4.0 H Small: 31.4 (#223), Phi 3 Mini 4k Instruct: 26.6 (#257)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Math12471111
Omni-MATH29.6%—
LiveBench Math—15.7%

Knowledge Granite 4.0 H Small leads

Granite 4.0 H Small: 32.0 (#215), Phi 3 Mini 4k Instruct: 28.5 (#246)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Expert12511045
MMLU-Pro56.9%—
Vectara Hallucination Rate5.2%—
GPQA (HELM)38.3%—
ARC (AI2) Challenge—84.9%
MMLU—68.8%
OpenBookQA—88%
TriviaQA—64%

Multilingual Granite 4.0 H Small leads

Granite 4.0 H Small: 38.6 (#228), Phi 3 Mini 4k Instruct: 26.3 (#280)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Non-English12161021
LMArena Chinese12491021
LMArena Russian12011022
LMArena Spanish12581085
LMArena French—1076
LMArena German—1044
LMArena Japanese—935
LMArena Korean—905

Instruction Following Granite 4.0 H Small leads

Granite 4.0 H Small: 68.7 (#183), Phi 3 Mini 4k Instruct: 47.7 (#303)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Instruction Following12221053
LiveBench Instruction Following—39.1%
IFEval89%—

Long Context Granite 4.0 H Small leads

Granite 4.0 H Small: 37.7 (#213), Phi 3 Mini 4k Instruct: 31.7 (#276)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Longer Query12421044

Writing & Preference Granite 4.0 H Small leads

Granite 4.0 H Small: 43.8 (#227), Phi 3 Mini 4k Instruct: 27.6 (#300)

BenchmarkGranite 4.0 H SmallPhi 3 Mini 4k Instruct
LMArena Text12411073
LMArena Creative Writing12111037
LMArena Multi-Turn12421018
WildBench73.9%—
LiveBench Language—9.2%

Frequently asked questions

Is Granite 4.0 H Small better than Phi 3 Mini 4k Instruct?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.9 on the Noometry Index.

Is Granite 4.0 H Small or Phi 3 Mini 4k Instruct better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 26.6 in the Noometry coding category.

How many benchmarks do Granite 4.0 H Small and Phi 3 Mini 4k Instruct share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.

Related comparisons

Go deeper