IBMGranite 4.0 H Small
Best configuration ranks #512 of 610 on the BenchLeader Index at 40.3 ±1.9. Released 22 Sept 2025.
- Blended price
- $0.108/M
- $0.060 in · $0.250 out
- Output speed
- 22 tok/s
- First answer
- 21 s
- first token 21 s
- Context
- 128k
- Overall index40
- Agents & tools36
- Knowledge35
- Instruction following35
- Long context31
- Composite37
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 | 41.6%#447 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 3.8%#479 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 2.3%#304 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 17.3%#336 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -61.0#394 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 31.5%#333 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 11.3%#390 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 6.0#457 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 34.5 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0009 | – | 48.0 s |
| Code edit | 6,000 / 1,500 | $0.0007 | – | 1.5 min |
| Agentic coding session | 60,000 / 4,000 | $0.0046 | – | 3.4 min |
| Structured extraction | 2,000 / 200 | $0.0002 | – | 30.0 s |
See also
Data as of 9 Sept 2026. Compare with another model.