Noometry

Model comparison

Claude Opus 5.5 vs Granite 4.0 H Small

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 36.5 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude Opus 5.5 Anthropic

68.6

Rank #3 Confirmed

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude Opus 5.5 scores higher in 8 categories and Granite 4.0 H Small in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 5.5 leads 91.8 to 31.4.
  • Granite 4.0 H Small has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5.5Granite 4.0 H Small
ProviderAnthropicIBM
Noometry Index68.636.5
Released2026-09-22—
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$4—
Output $ / M tokens$20—
Results tracked4419

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

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 5.5: 71.9 (#3), Granite 4.0 H Small: 36.4 (#209)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Coding15471249
FrontierCode54.6%—
CursorBench57.8%—
LMArena WebDev1813—
FrontierSWE62.3%—
SciCode66.9%—
MirrorCode77.4%—
ALE-Bench2,147—

Agentic & Tool Use Not comparable

Claude Opus 5.5: 45.3 (#15), Granite 4.0 H Small: —

BenchmarkClaude Opus 5.5Granite 4.0 H Small
APEX-Agents73.5%—
GDP.pdf30.6%—
Vending-Bench 29,235—

Reasoning Claude Opus 5.5 leads

Claude Opus 5.5: 80.2 (#3), Granite 4.0 H Small: 24.4 (#163)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Hard Prompts15351240
ARC-AGI-293.3%—
NYT Connections (extended)88.5%—
ARC-AGI-198.5%—
CritPt31.7%—
EBR-Bench71.4%—
Mystery Game Puzzles71%—
DTBench98.9%—
LMCA68.2%—
Epoch Capabilities Index167.33—

Math Claude Opus 5.5 leads

Claude Opus 5.5: 91.8 (#3), Granite 4.0 H Small: 31.4 (#223)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Math15061247
FrontierMath (Tiers 1-3)91.2%—
FrontierMath Tier 495%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
Omni-MATH—29.6%
FrontierMath Erdős2.9%—

Knowledge Claude Opus 5.5 leads

Claude Opus 5.5: 66.4 (#10), Granite 4.0 H Small: 32.0 (#215)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Expert15471251
GPQA Diamond90.6%—
SimpleQA Verified72.2%—
MMLU-Pro—56.9%
Vectara Hallucination Rate—5.2%
GPQA (HELM)—38.3%

Multimodal Not comparable

Claude Opus 5.5: 57.8 (#1), Granite 4.0 H Small: —

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Vision1321—
Blueprint-Bench 251.2%—
Furniture Assembly83.3%—

Multilingual Claude Opus 5.5 leads

Claude Opus 5.5: 59.1 (#2), Granite 4.0 H Small: 38.6 (#228)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Non-English15071216
LMArena Chinese15881249
LMArena Russian15201201
LMArena Spanish15071258
LMArena French1514—

Instruction Following Claude Opus 5.5 leads

Claude Opus 5.5: 80.0 (#3), Granite 4.0 H Small: 68.7 (#183)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Instruction Following15371222
IFEval—89%

Long Context Claude Opus 5.5 leads

Claude Opus 5.5: 47.1 (#19), Granite 4.0 H Small: 37.7 (#213)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Longer Query15321242

Writing & Preference Claude Opus 5.5 leads

Claude Opus 5.5: 78.2 (#3), Granite 4.0 H Small: 43.8 (#227)

BenchmarkClaude Opus 5.5Granite 4.0 H Small
LMArena Text15151241
LMArena Creative Writing15331211
LMArena Multi-Turn14991242
EQ-Bench Creative Writing2050—
WildBench—73.9%

Frequently asked questions

Is Claude Opus 5.5 better than Granite 4.0 H Small?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 36.5 on the Noometry Index.

Is Claude Opus 5.5 or Granite 4.0 H Small better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 36.4 in the Noometry coding category.

How many benchmarks do Claude Opus 5.5 and Granite 4.0 H Small share?

13 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Granite 4.0 H Small has 19.

Related comparisons

Go deeper