IBM
Granite 4.0 H Small
Granite 4.0 H Small is a IBM language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.
IBM Granite modelsOperational Metrics
Output Speed238.9 tok/s
First Token8.67s
Blended Price$0.107/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseSep 22, 2025
Context Windown/a
Modalitiesn/a
Strength: Speed
Rank #12 across 293 models.
238.9 tok/s
Strength: Input $
Rank #21 across 325 models.
$0.060/M
Strength: Blended $
Rank #23 across 325 models.
$0.107/M
Watch Area: HLE
Rank #438 across 474 models.
3.7%
Watch Area: TTFT
Rank #255 across 293 models.
8.67s
Watch Area: Math
Rank #224 across 269 models.
13.7
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 10.8 | #401 |
| Artificial Analysis Coding Index | coding | 8.5 | #334 |
| Artificial Analysis Math Index | math | 13.7 | #224 |
| MMLU-Pro | reasoning | 62.4% | #262 |