Noometry

Model comparison

Granite 4.0 Micro vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 2.1× less per token, which makes it the better buy when Phi-4's lead doesn't matter for your workload.

Last verified . 3 shared benchmarks.

Granite 4.0 Micro IBM

29.0

Rank #318 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Granite 4.0 Micro scores higher in 3 categories and Phi-4 in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Phi-4 leads 32.6 to 9.9.
  • The biggest single-benchmark swing is GPQA Diamond: 28.3% for Granite 4.0 Micro and 56.1% for Phi-4.
  • Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.07 / $0.14 for Phi-4.
  • Granite 4.0 Micro accepts more context: 131K tokens versus 128K.

Side by side

Granite 4.0 MicroPhi-4
ProviderIBMMicrosoft
Noometry Index29.031.2
Released2025-10-022024-12-11
WeightsOpenOpen
Context window131K128K
Max output118K4K
Input $ / M tokens$0.017$0.07
Output $ / M tokens$0.11$0.14
Results tracked837

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

Category by category

Coding Not comparable

Granite 4.0 Micro: —, Phi-4: 34.4 (#239)

BenchmarkGranite 4.0 MicroPhi-4
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
LMArena Coding—1231
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

Granite 4.0 Micro: —, Phi-4: 22.8 (#128)

BenchmarkGranite 4.0 MicroPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Granite 4.0 Micro leads

Granite 4.0 Micro: 19.2 (#265), Phi-4: 17.7 (#291)

BenchmarkGranite 4.0 MicroPhi-4
Chess Puzzles0%1%
LiveBench Reasoning—47.8%
LMArena Hard Prompts—1220
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.42
LiveBench—41.6%

Math Phi-4 leads

Granite 4.0 Micro: 12.0 (#307), Phi-4: 20.8 (#285)

BenchmarkGranite 4.0 MicroPhi-4
OTIS Mock AIME 2024-20252.8%13.8%
Omni-MATH20.9%—
LiveBench Math—42%
LMArena Math—1246
MATH Level 5—64.9%

Knowledge Phi-4 leads

Granite 4.0 Micro: 9.9 (#304), Phi-4: 32.6 (#209)

BenchmarkGranite 4.0 MicroPhi-4
GPQA Diamond28.3%56.1%
MMLU-Pro39.5%—
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
GPQA (HELM)30.7%—
LMArena Expert—1203
MMLU—84.8%

Multilingual Not comparable

Granite 4.0 Micro: —, Phi-4: 37.2 (#237)

BenchmarkGranite 4.0 MicroPhi-4
LMArena Non-English—1197
LMArena Chinese—1212
LMArena French—1224
LMArena German—1222
LMArena Japanese—1158
LMArena Korean—1151
LMArena Russian—1209
LMArena Spanish—1234

Instruction Following Granite 4.0 Micro leads

Granite 4.0 Micro: 69.9 (#169), Phi-4: 60.4 (#251)

BenchmarkGranite 4.0 MicroPhi-4
LiveBench Instruction Following—58.4%
IFEval84.9%—
LMArena Instruction Following—1201

Long Context Not comparable

Granite 4.0 Micro: —, Phi-4: 36.9 (#226)

BenchmarkGranite 4.0 MicroPhi-4
LMArena Longer Query—1217

Writing & Preference Granite 4.0 Micro leads

Granite 4.0 Micro: 46.7 (#216), Phi-4: 40.5 (#244)

BenchmarkGranite 4.0 MicroPhi-4
LMArena Text—1217
LMArena Creative Writing—1182
Short-Story Creative Writing—62.6%
WildBench67%—
LMArena Multi-Turn—1206
LiveBench Language—25.6%

Frequently asked questions

Is Granite 4.0 Micro better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 2.1× less per token, which makes it the better buy when Phi-4's lead doesn't matter for your workload.

Which is cheaper, Granite 4.0 Micro or Phi-4?

Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Phi-4 lists at $0.07 and $0.14.

Which has the bigger context window?

Granite 4.0 Micro does, with 131K tokens against 128K.

How many benchmarks do Granite 4.0 Micro and Phi-4 share?

3 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper