Noometry

Model comparison

GPT-4 vs Granite 4.2 8B

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 29.1 on the Noometry Index.

Last verified . 11 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Granite 4.2 8B in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 18.4.
  • Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $30 / $60 for GPT-4.
  • Granite 4.2 8B accepts more context: 131K tokens versus 8K.
  • Granite 4.2 8B has downloadable open weights; the other is API-only.

Side by side

GPT-4Granite 4.2 8B
ProviderOpenAIIBM
Noometry Index29.140.5
Released2023-03-14—
WeightsProprietaryOpen
Context window8K131K
Max output8K118K
Input $ / M tokens$30$0.06
Output $ / M tokens$60$0.25
Results tracked3811

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

Category by category

Coding Granite 4.2 8B leads

GPT-4: 31.6 (#283), Granite 4.2 8B: 40.5 (#137)

BenchmarkGPT-4Granite 4.2 8B
LMArena Coding12541380
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Granite 4.2 8B: —

BenchmarkGPT-4Granite 4.2 8B
METR Time Horizons36.1%—

Reasoning Granite 4.2 8B leads

GPT-4: 17.8 (#289), Granite 4.2 8B: 26.6 (#131)

BenchmarkGPT-4Granite 4.2 8B
LMArena Hard Prompts12411329
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Not comparable

GPT-4: 10.8 (#309), Granite 4.2 8B: —

BenchmarkGPT-4Granite 4.2 8B
OTIS Mock AIME 2024-20251.1%—
LMArena Math1269—
MATH Level 523%—
GSM8K92%—

Knowledge Granite 4.2 8B leads

GPT-4: 18.4 (#282), Granite 4.2 8B: 38.4 (#145)

BenchmarkGPT-4Granite 4.2 8B
LMArena Expert12111384
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multilingual Granite 4.2 8B leads

GPT-4: 40.6 (#215), Granite 4.2 8B: 44.5 (#178)

BenchmarkGPT-4Granite 4.2 8B
LMArena Non-English12461302
LMArena Chinese12421366
LMArena Russian12511285
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Granite 4.2 8B leads

GPT-4: 65.3 (#222), Granite 4.2 8B: 68.7 (#184)

BenchmarkGPT-4Granite 4.2 8B
LMArena Instruction Following12411301

Long Context Granite 4.2 8B leads

GPT-4: 37.7 (#212), Granite 4.2 8B: 40.3 (#159)

BenchmarkGPT-4Granite 4.2 8B
LMArena Longer Query12441324

Writing & Preference Granite 4.2 8B leads

GPT-4: 34.9 (#268), Granite 4.2 8B: 49.6 (#189)

BenchmarkGPT-4Granite 4.2 8B
LMArena Text12631320
LMArena Creative Writing12441236
LMArena Multi-Turn12571301
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Granite 4.2 8B?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Granite 4.2 8B?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Granite 4.2 8B better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Granite 4.2 8B does, with 131K tokens against 8K.

How many benchmarks do GPT-4 and Granite 4.2 8B share?

11 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Granite 4.2 8B has 11.

Related comparisons

Go deeper