IBMAuto-detectedGranite 4.1 30B
Best configuration ranks #506 of 610 on the BenchLeader Index at 40.4 ±5.2. Last measured 29 Apr 2026. Released 29 Apr 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 131k
- Overall index40
- Coding25
- Agents & tools36
- Knowledge32
- Instruction following46
- Long context37
- Composite38
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 48.1%#415 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.1%#455 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 2.3%#304 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 42.1%#212 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -67.8#429 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 44.4%#208 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 23.7%#347 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 7.4#395 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.