Noometry

Model comparison

GPT-5.4 mini vs Granite 4.2 3b

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.4 on the Noometry Index.

Last verified . 11 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Granite 4.2 3b IBM

39.4

Rank #169 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GPT-5.4 mini scores higher in 7 categories and Granite 4.2 3b in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.4 mini leads 64.0 to 47.2.
  • Granite 4.2 3b has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniGranite 4.2 3b
ProviderOpenAIIBM
Noometry Index45.039.4
Released2026-03-17—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4611

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Granite 4.2 3b: 40.0 (#151)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Coding14381361
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.9 (#81), Granite 4.2 3b: —

BenchmarkGPT-5.4 miniGranite 4.2 3b
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Granite 4.2 3b: 26.0 (#138)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Hard Prompts14241306
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.84—
ForecastBench57—

Math Not comparable

GPT-5.4 mini: 45.5 (#75), Granite 4.2 3b: —

BenchmarkGPT-5.4 miniGranite 4.2 3b
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
LMArena Math1419—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Granite 4.2 3b: 36.3 (#171)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Expert14351315
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Granite 4.2 3b: —

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Granite 4.2 3b: 42.1 (#198)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Non-English14051268
LMArena Chinese14461269
LMArena Russian14171249
LMArena French1440—
LMArena German1409—
LMArena Japanese1374—
LMArena Korean1368—
LMArena Spanish1405—

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Granite 4.2 3b: 67.1 (#200)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Instruction Following14051273

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Granite 4.2 3b: 39.2 (#185)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Longer Query14071291

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Granite 4.2 3b: 47.2 (#212)

BenchmarkGPT-5.4 miniGranite 4.2 3b
LMArena Text14121293
LMArena Creative Writing13701205
LMArena Multi-Turn14291290
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Granite 4.2 3b?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.4 on the Noometry Index.

Is GPT-5.4 mini or Granite 4.2 3b better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 40.0 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Granite 4.2 3b share?

11 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Granite 4.2 3b has 11.

Related comparisons

Go deeper