IBM model product
Granite 3.3 models feature enhanced reasoning capabilities and support for Fill-in-the-Middle (FIM) code completion. They are built on a foundation of open-source instruction datasets with permissive licenses, alongside internally curated synthetic datasets tailored for long-context problem-solving. These models preserve the key strengths of previous Granite versions, including support for a 128K context length, strong performance in retrieval-augmented generation (RAG) and function calling, and controls for response length and originality. Granite 3.3 also delivers competitive results across general, enterprise, and safety benchmarks. Released as open source, the models are available under the Apache 2.0 license.
Updated Aug 10, 2026. Default version: Granite 3.3 8B Instruct
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Granite 3.3 8B Instruct.
| AlpacaEval 2.0 | 0.6 | 2 | 4 | 66.7% | C | |
| AttaQ | 0.9 | 2 | 3 | 50.0% | C | |
| PopQA | 0.3 | 2 | 3 | 50.0% | C | |
| TruthfulQA | 0.7 | 3 | 18 | 88.2% | C | |
| BIG-Bench Hard | 0.7 | 14 | 21 | 35.0% | C | |
| Arena Hard | 0.6 | 15 | 26 | 44.0% | C | |
| HumanEval | 0.9 | 16 | 76 | 80.0% | C | |
| DROP | 0.6 | 25 | 30 | 17.2% | C | |
| AIME 2024 | 0.8 | 26 | 53 | 51.9% | C | |
| MATH-500 | 0.7 | 32 | 32 | 0.0% | C | |
| HumanEval+ | 0.9 | 35 | 76 | 54.7% | C | |
| GSM8k | 0.8 | 38 | 48 | 21.3% | C | |
| IFEval | 0.7 | 59 | 65 | 9.4% | C | |
| MMLU | 0.7 | 91 | 100 | 9.1% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
The default version has no provider offering with current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Granite 3.3 8B Base | N/A | 8.2B | N/A | N/A | No | Apache 2.0 | |
| Granite 3.3 8B Instruct | 45.0 | 8B | 128K | 8.2K | No | Apache 2.0 |
A concise description based on the published model registry.
Granite 3.3 models feature enhanced reasoning capabilities and support for Fill-in-the-Middle (FIM) code completion. They are built on a foundation of open-source instruction datasets with permissive licenses, alongside internally curated synthetic datasets tailored for long-context problem-solving. These models preserve the key strengths of previous Granite versions, including support for a 128K context length, strong performance in retrieval-augmented generation (RAG) and function calling, and controls for response length and originality. Granite 3.3 also delivers competitive results across general, enterprise, and safety benchmarks. Released as open source, the models are available under the Apache 2.0 license.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Granite 3.3 8B.
Granite 3.3 8B's default version was released on Apr 16, 2025.
No official standard PAYG price is currently available for Granite 3.3 8B.
Granite 3.3 8B is published under IBM in the model registry.
The default version has a 128K token context window.
No. The default version is not marked as having publicly available weights.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include Qwen2.5 Coder 32B, Gemma 3 27B, Nemotron 3 Nano.