Noometry

Model comparison

GPT-4.5 vs Granite 3.1 8b Instruct

GPT-4.5 is the stronger model overall, scoring 37.2 to 32.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Granite 3.1 8b Instruct IBM

32.4

Rank #258 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and Granite 3.1 8b Instruct in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where GPT-4.5 leads 52.5 to 30.9.
  • Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Granite 3.1 8b Instruct
ProviderOpenAIIBM
Noometry Index37.232.4
Released2025-02-27—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4213

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Granite 3.1 8b Instruct: 34.5 (#233)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Coding13961186
Aider Polyglot44.9%—
WeirdML39.4%—
LiveBench Coding75.2%—

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), Granite 3.1 8b Instruct: 24.1 (#120)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
Berkeley Function Calling Leaderboard—27.1%
Cybench17.5%—

Reasoning Granite 3.1 8b Instruct leads

GPT-4.5: 13.9 (#330), Granite 3.1 8b Instruct: 22.1 (#207)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Hard Prompts14031145
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
Epoch Capabilities Index136.74—
ForecastBench61.7—
LiveBench69%—

Math Too close to call

GPT-4.5: 32.6 (#211), Granite 3.1 8b Instruct: 33.0 (#209)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Math14121152
OTIS Mock AIME 2024-202537.8%—
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Granite 3.1 8b Instruct: 31.1 (#220)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Expert13941142
GPQA Diamond68.7%—
Humanity's Last Exam5.4%—
Confabulations13.6%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Granite 3.1 8b Instruct: —

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Granite 3.1 8b Instruct: 30.9 (#260)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Non-English14131099
LMArena Chinese14211145
LMArena Russian14191092
LMArena French1418—
LMArena German1457—
LMArena Japanese1416—
LMArena Korean1392—

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Granite 3.1 8b Instruct: 58.6 (#259)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Instruction Following14041131
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Granite 3.1 8b Instruct: 35.2 (#241)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Longer Query14061162
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Granite 3.1 8b Instruct: 35.5 (#266)

BenchmarkGPT-4.5Granite 3.1 8b Instruct
LMArena Text14171150
LMArena Creative Writing13941129
LMArena Multi-Turn14441108
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Granite 3.1 8b Instruct?

GPT-4.5 is the stronger model overall, scoring 37.2 to 32.4 on the Noometry Index.

Is GPT-4.5 or Granite 3.1 8b Instruct better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 34.5 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Granite 3.1 8b Instruct share?

12 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Granite 3.1 8b Instruct has 13.

Related comparisons

Go deeper