IBM
Granite 4.0 H Small
Granite 4.0 H Small by IBM — compare inference API pricing across providers.
Contact providers for pricing
API Pricing
No pricing data available for this model at the moment.
Prices updated daily. Last check: Jul 16, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
5.2 / 100
Math
13.7 / 100
Output Speed
438 t/s
Latency (TTFT)
8.8s
Reasoning & Knowledge
- MMLU-Pro62.4%
- GPQA Diamond41.6%
- Humanity's Last Exam3.7%
Coding
- LiveCodeBench25.1%
- SciCode20.9%
Math
- AIME 202513.7%
Agentic & Tool Use
- Terminal-Bench Hard2.3%
- τ²-bench17.3%
Instruction & Long Context
- IFBench31.5%
- Long-Context Reasoning9.0%
Benchmarks measured Jul 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- IBM
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No