Noometry

Model comparison

GPT-4.1 mini vs Granite 4.1 8b

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 33.5 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-4.1 mini OpenAI

33.5

Rank #232 Confirmed

Granite 4.1 8b IBM

36.8

Rank #202 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-4.1 mini scores higher in 4 categories and Granite 4.1 8b in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Granite 4.1 8b leads 24.6 to 10.9.
  • Granite 4.1 8b has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniGranite 4.1 8b
ProviderOpenAIIBM
Noometry Index33.536.8
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4713

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

Category by category

Coding Too close to call

GPT-4.1 mini: 30.4 (#286), Granite 4.1 8b: 29.9 (#291)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Coding13671313
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
LMArena WebDev—1190
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.0 (#52), Granite 4.1 8b: —

BenchmarkGPT-4.1 miniGranite 4.1 8b
Berkeley Function Calling Leaderboard50.5%—

Reasoning Granite 4.1 8b leads

GPT-4.1 mini: 10.9 (#335), Granite 4.1 8b: 24.6 (#142)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Hard Prompts13491294
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math Granite 4.1 8b leads

GPT-4.1 mini: 23.1 (#264), Granite 4.1 8b: 33.8 (#167)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Math13431311
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Too close to call

GPT-4.1 mini: 34.7 (#183), Granite 4.1 8b: 35.5 (#171)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Expert13381310
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.2 (#77), Granite 4.1 8b: —

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Vision1181—

Multilingual GPT-4.1 mini leads

GPT-4.1 mini: 45.9 (#161), Granite 4.1 8b: 41.8 (#199)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Non-English13181261
LMArena Chinese13291335
LMArena Russian13241238
LMArena French1357—
LMArena German1349—
LMArena Japanese1291—
LMArena Korean1298—
LMArena Spanish1319—

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.9 (#113), Granite 4.1 8b: 67.0 (#198)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Instruction Following13321268
IFEval90.4%—

Long Context Granite 4.1 8b leads

GPT-4.1 mini: 31.8 (#270), Granite 4.1 8b: 38.7 (#188)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Longer Query13441275
Fiction.LiveBench44.4%—

Writing & Preference Too close to call

GPT-4.1 mini: 48.8 (#193), Granite 4.1 8b: 48.3 (#199)

BenchmarkGPT-4.1 miniGranite 4.1 8b
LMArena Text13411291
LMArena Creative Writing13001249
LMArena Multi-Turn13541269
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Granite 4.1 8b?

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 33.5 on the Noometry Index.

Is GPT-4.1 mini or Granite 4.1 8b better for coding?

They score almost the same on coding (30.4 vs 29.9); test both on your own repository before choosing.

How many benchmarks do GPT-4.1 mini and Granite 4.1 8b share?

12 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Granite 4.1 8b has 13.

Related comparisons

Go deeper