Noometry

Model comparison

Claude 3 Sonnet vs Granite 4.0 H Small

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Granite 4.0 H Small in 8 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 10.7.
  • Granite 4.0 H Small has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGranite 4.0 H Small
ProviderAnthropicIBM
Noometry Index29.036.5
Released2024-02-29—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3019

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

Category by category

Coding Granite 4.0 H Small leads

Claude 3 Sonnet: 29.6 (#302), Granite 4.0 H Small: 36.4 (#209)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Coding12231249
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Granite 4.0 H Small leads

Claude 3 Sonnet: 20.5 (#237), Granite 4.0 H Small: 24.4 (#163)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Hard Prompts11971240
DTBench53.6%—
Epoch Capabilities Index120.7—
WinoGrande75.1%—

Math Granite 4.0 H Small leads

Claude 3 Sonnet: 10.7 (#310), Granite 4.0 H Small: 31.4 (#223)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Math12131247
OTIS Mock AIME 2024-20252.5%—
Omni-MATH—29.6%
MATH Level 518.2%—

Knowledge Granite 4.0 H Small leads

Claude 3 Sonnet: 21.1 (#276), Granite 4.0 H Small: 32.0 (#215)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Expert11731251
GPQA Diamond40.6%—
MMLU-Pro—56.9%
Vectara Hallucination Rate—5.2%
GPQA (HELM)—38.3%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Granite 4.0 H Small: —

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Vision984—

Multilingual Too close to call

Claude 3 Sonnet: 37.8 (#234), Granite 4.0 H Small: 38.6 (#228)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Non-English12051216
LMArena Chinese11891249
LMArena Russian12271201
LMArena Spanish12041258
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—

Instruction Following Granite 4.0 H Small leads

Claude 3 Sonnet: 62.8 (#235), Granite 4.0 H Small: 68.7 (#183)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Instruction Following11991222
IFEval—89%

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Granite 4.0 H Small: 37.7 (#213)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Longer Query12111242

Writing & Preference Granite 4.0 H Small leads

Claude 3 Sonnet: 42.1 (#238), Granite 4.0 H Small: 43.8 (#227)

BenchmarkClaude 3 SonnetGranite 4.0 H Small
LMArena Text12181241
LMArena Creative Writing11861211
LMArena Multi-Turn12271242
WildBench—73.9%

Frequently asked questions

Is Claude 3 Sonnet better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Granite 4.0 H Small share?

13 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Granite 4.0 H Small has 19.

Related comparisons

Go deeper