Noometry

Model comparison

Claude 3.5 Haiku vs Granite 4.2 30b

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 29.2 on the Noometry Index.

Last verified . 11 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Granite 4.2 30b IBM

41.8

Rank #130 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Granite 4.2 30b in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Granite 4.2 30b leads 39.1 to 18.7.
  • Granite 4.2 30b has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuGranite 4.2 30b
ProviderAnthropicIBM
Noometry Index29.241.8
Released2024-10-22—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4911

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

Category by category

Coding Granite 4.2 30b leads

Claude 3.5 Haiku: 32.9 (#265), Granite 4.2 30b: 41.0 (#126)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Coding12861396
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Granite 4.2 30b: —

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
BALROG19.3%—

Reasoning Granite 4.2 30b leads

Claude 3.5 Haiku: 17.7 (#290), Granite 4.2 30b: 27.8 (#112)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Hard Prompts12511374
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Not comparable

Claude 3.5 Haiku: 14.7 (#300), Granite 4.2 30b: —

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
LMArena Math1244—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Granite 4.2 30b leads

Claude 3.5 Haiku: 18.7 (#281), Granite 4.2 30b: 39.1 (#138)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Expert12081406
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Granite 4.2 30b: —

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Vision1092—
GeoBench34%—

Multilingual Granite 4.2 30b leads

Claude 3.5 Haiku: 40.0 (#218), Granite 4.2 30b: 47.3 (#151)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Non-English12381340
LMArena Chinese12291414
LMArena Russian12531343
LMArena French1264—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—
LMArena Spanish1261—

Instruction Following Granite 4.2 30b leads

Claude 3.5 Haiku: 62.9 (#234), Granite 4.2 30b: 71.2 (#155)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Instruction Following12411347
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Granite 4.2 30b leads

Claude 3.5 Haiku: 38.3 (#200), Granite 4.2 30b: 41.4 (#140)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Longer Query12611359

Writing & Preference Granite 4.2 30b leads

Claude 3.5 Haiku: 42.7 (#234), Granite 4.2 30b: 53.8 (#156)

BenchmarkClaude 3.5 HaikuGranite 4.2 30b
LMArena Text12551361
LMArena Creative Writing12331288
LMArena Multi-Turn12651339
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Granite 4.2 30b?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Granite 4.2 30b better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Granite 4.2 30b share?

11 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Granite 4.2 30b has 11.

Related comparisons

Go deeper