IBMGranite 4.1 8B
Best configuration ranks #498 of 610 on the BenchLeader Index at 40.9 ±5.2. Last measured 8 Sept 2026. Released 29 Apr 2026.
- Blended price
- $0.063/M
- $0.050 in · $0.100 out
- Output speed
- 80 tok/s
- First answer
- 0.81 s
- first token 0.81 s
- Context
- 131k
- Overall index41
- Reasoning48
- Coding31
- Agents & tools34
- Knowledge34
- Instruction following41
- Human preference47
- Long context32
- 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 | Trend |
|---|---|---|---|
| LMArena Hard Prompts | 1321#220 | LMArena | |
| GPQA Diamond (AA)not in index | 43.3%#434 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.8%#479 | Artificial Analysis |
Coding
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Coding | 1354#219 | LMArena | |
| LMArena WebDev | 1192#114 | LMArena |
Agents & tools
| Benchmark | default | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 0.0%#345 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 27.8%#264 | Artificial Analysis |
Knowledge
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -64.1#417 | Artificial Analysis |
Instruction following
| Benchmark | default | Source | Trend |
|---|---|---|---|
| IFBench | 38.6%#266 | Artificial Analysis |
Human preference
| Benchmark | default | Source | Trend |
|---|---|---|---|
| LMArena Text | 1306#228 | LMArena |
Long context
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA-LCR | 13.3%#385 | Artificial Analysis |
Composite
| Benchmark | default | Source | Trend |
|---|---|---|---|
| AA Intelligence Index | 6.6#437 | 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 | – | 4.6 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0007 | – | 8.3 s |
| Code edit | 6,000 / 1,500 | $0.0005 | – | 19.6 s |
| Agentic coding session | 60,000 / 4,000 | $0.0034 | – | 51.0 s |
| Structured extraction | 2,000 / 200 | $0.0001 | – | 3.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.