Granite 4.1 30B
Granite 4.1 30B is a released coding, agents, and long context model with open-source and 131k context; evaluate it while provider pricing coverage matures.
Use it for
- Teams evaluating coding, agents, and long context
- Workloads that can use a 131k context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Granite 4.1
- Released
- 2026-04-29
- Context
- 131k
- Parameters
- 30B
- Architecture
- Decoder Only
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
No tracked provider token pricing is available yet.
About
IBM Granite 4.1 30B is the largest dense instruct model in the Granite 4.1 family. Supports multilingual dialog (12 languages), code, tool-calling, and long-context tasks. Benchmarks: HumanEval 89.63, GSM8K 94.16, IFEval 89.65, BFCL v3 73.68. Apache 2.0.
Top use-case fit: coding, agents, and build tasks
Coding
2 relevant benchmarks in the decision map.
Agents
1 relevant benchmark in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
Benchmark scores(7)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| MMLU PRO | 80.2 | —Observed 2026-04-29 | — | Source |
| HumanEval | 89.6 | pass@1, instruct model (pass@1)Observed 2026-06-07 | — | Source |
| Berkeley Function Calling Leaderboard v3 | 73.7 | BFCL v3 (accuracy)Observed 2026-06-07 | — | Source |
| BigCodeBench | 38.8 | BigCodeBench (pass@1)Observed 2026-06-07 | — | Source |
| Google-Proof Q&A | 45.8 | 0-shot CoT, instruct model (accuracy)Observed 2026-06-07 | — | Source |
| Grade School Math 8K | 94.2 | 8-shot, instruct model (accuracy)Observed 2026-06-07 | — | Source |
| Massive Multitask Language Understanding | 80.2 | 5-shot, instruct model (accuracy)Observed 2026-06-07 | — | Source |
Migration checks
No linked migration route is available for this model yet.
No tracked provider token pricing is available yet.