IBMAuto-detectedgranite-4.0-350m
Best configuration ranks #606 of 610 on the BenchLeader Index at 32.5 ±5.0. Last measured 28 Oct 2025stale: no new result in six months. Released 28 Oct 2025.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 33k
- Overall index33
- Reasoning12
- Agents & tools33
- Maths24
- Knowledge31
- Instruction following22
- Long context25
- Composite35
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 | 11.2%#271 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 26.1%#507 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 5.5%#347 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 0.0%#345 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 13.2%#356 | Artificial Analysis |
| BFCL Overall | 19.0%#77 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 0.3%#253 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -69.3#435 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 15.9%#399 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 0.0%#419 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 4.8#527 | Artificial Analysis |
See also
Data as of 9 Sept 2026. Compare with another model.