Noometry

Model comparison

GPT-4.1 vs Granite 4.1 8b

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 35.7 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

Granite 4.1 8b IBM

36.8

Rank #202 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and Granite 4.1 8b in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Granite 4.1 8b leads 24.6 to 11.7.
  • Granite 4.1 8b has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Granite 4.1 8b
ProviderOpenAIIBM
Noometry Index35.736.8
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5213

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

Category by category

Coding GPT-4.1 leads

GPT-4.1: 34.2 (#228), Granite 4.1 8b: 29.9 (#291)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Coding13911313
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
LMArena WebDev—1190
WeirdML39%—
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use Not comparable

GPT-4.1: 34.4 (#40), Granite 4.1 8b: —

BenchmarkGPT-4.1Granite 4.1 8b
Berkeley Function Calling Leaderboard54%—

Reasoning Granite 4.1 8b leads

GPT-4.1: 11.7 (#334), Granite 4.1 8b: 24.6 (#142)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Hard Prompts13841294
ARC-AGI-20.4%—
SimpleBench27%—
Kagi LLM Benchmark52.3%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
DTBench68.3%—
LMCA25.6%—
Epoch Capabilities Index136.79—
ForecastBench61.5—

Math Granite 4.1 8b leads

GPT-4.1: 21.4 (#269), Granite 4.1 8b: 33.8 (#167)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Math13691311
FrontierMath (Tiers 1-3)6%—
OTIS Mock AIME 2024-202538.3%—
Omni-MATH47.1%—
MATH Level 583%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.0 (#152), Granite 4.1 8b: 35.5 (#171)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Expert13641310
GPQA Diamond66.9%—
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—

Multimodal Not comparable

GPT-4.1: 37.5 (#66), Granite 4.1 8b: —

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Vision1210—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.6 (#128), Granite 4.1 8b: 41.8 (#199)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Non-English13701261
LMArena Chinese13821335
LMArena Russian13771238
LMArena French1383—
LMArena German1380—
LMArena Japanese1320—
LMArena Korean1339—
LMArena Spanish1375—

Instruction Following GPT-4.1 leads

GPT-4.1: 71.5 (#148), Granite 4.1 8b: 67.0 (#198)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Instruction Following13671268
IFEval83.8%—

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#158), Granite 4.1 8b: 38.7 (#188)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Longer Query13851275
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.8 (#120), Granite 4.1 8b: 48.3 (#199)

BenchmarkGPT-4.1Granite 4.1 8b
LMArena Text13831291
LMArena Creative Writing13631249
LMArena Multi-Turn13981269
EQ-Bench Creative Writing1420—
WildBench85.4%—

Frequently asked questions

Is GPT-4.1 better than Granite 4.1 8b?

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 35.7 on the Noometry Index.

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

GPT-4.1 scores higher on coding benchmarks: 34.2 versus 29.9 in the Noometry coding category.

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

12 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Granite 4.1 8b has 13.

Related comparisons

Go deeper