IBM
Granite 3.3 8B
Granite 3.3 8B 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: Jun 23, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
1.8 / 100
Math
6.7 / 100
Output Speed
446 t/s
Latency (TTFT)
21.5s
Reasoning & Knowledge
- MMLU-Pro46.8%
- GPQA Diamond33.8%
- Humanity's Last Exam4.2%
Coding
- LiveCodeBench12.7%
- SciCode10.1%
Math
- AIME 20256.7%
- AIME4.7%
- MATH-50066.5%
Agentic & Tool Use
- Terminal-Bench Hard0.0%
- τ²-bench10.5%
Instruction & Long Context
- IFBench22.4%
- Long-Context Reasoning4.3%
Benchmarks measured Jun 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- IBM
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No