Noometry

Model comparison

Claude 3 Opus vs Granite 4.0 H Small

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.5 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and Granite 4.0 H Small in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 14.8.
  • Granite 4.0 H Small has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusGranite 4.0 H Small
ProviderAnthropicIBM
Noometry Index29.536.5
Released2024-02-29—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4619

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

Category by category

Coding Granite 4.0 H Small leads

Claude 3 Opus: 32.9 (#267), Granite 4.0 H Small: 36.4 (#209)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Coding12641249
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Granite 4.0 H Small: —

BenchmarkClaude 3 OpusGranite 4.0 H Small
Cybench10%—
METR Time Horizons29.5%—

Reasoning Granite 4.0 H Small leads

Claude 3 Opus: 14.6 (#324), Granite 4.0 H Small: 24.4 (#163)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Hard Prompts12451240
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Granite 4.0 H Small leads

Claude 3 Opus: 14.8 (#299), Granite 4.0 H Small: 31.4 (#223)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Math12731247
OTIS Mock AIME 2024-20254.7%—
Omni-MATH—29.6%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge Granite 4.0 H Small leads

Claude 3 Opus: 24.5 (#267), Granite 4.0 H Small: 32.0 (#215)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Expert12231251
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
MMLU-Pro—56.9%
Confabulations22.7%—
Vectara Hallucination Rate—5.2%
GPQA (HELM)—38.3%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Granite 4.0 H Small: —

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Granite 4.0 H Small: 38.6 (#228)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Non-English12581216
LMArena Chinese12481249
LMArena Russian12801201
LMArena Spanish12461258
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—

Instruction Following Granite 4.0 H Small leads

Claude 3 Opus: 64.1 (#228), Granite 4.0 H Small: 68.7 (#183)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Instruction Following12481222
LiveBench Instruction Following63.9%—
IFEval—89%

Long Context Too close to call

Claude 3 Opus: 38.2 (#202), Granite 4.0 H Small: 37.7 (#213)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Longer Query12591242

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Granite 4.0 H Small: 43.8 (#227)

BenchmarkClaude 3 OpusGranite 4.0 H Small
LMArena Text12621241
LMArena Creative Writing12351211
LMArena Multi-Turn12751242
WildBench—73.9%
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.5 on the Noometry Index.

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

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 32.9 in the Noometry coding category.

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

13 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Granite 4.0 H Small has 19.

Related comparisons

Go deeper