Granite 4.1 8B
IBM Granite · released Apr 30, 2026
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
Specification
- Context window
- 131K
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 8.8B
- Licence
- apache-2.0
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
6.4
20th percentile
Coding
9.5
Coding Index
Agentic
—
Agentic Index
Output speed
121 t/s
Median across providers
Latency
118ms
Time to first token
Cost per task
$0.005
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond43.3%
- IFBench38.6%
- τ²-bench (Telecom)27.8%
- SciCode21.8%
- AA-LCR (long context)11.3%
- Humanity's Last Exam3.8%
- Terminal-Bench Hard0.0%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 43.3% |
| IFBench | 38.6% |
| τ²-bench (Telecom) | 27.8% |
| SciCode | 21.8% |
| AA-LCR (long context) | 11.3% |
| Humanity's Last Exam | 3.8% |
| Terminal-Bench Hard | 0.0% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GLM 4.5VZ.ai6.8
- GPT-4OpenAI6.8
- Gemini 2.5 Flash LiteGoogle6.7
- GPT-4o-miniOpenAI6.7
- GPT-4o-mini (2024-07-18)OpenAI6.7
- Granite 4.1 8BIBM Granite6.4
- SabaMistral AI6.2
- Olmo 3 32B ThinkAllen AI6.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GLM 4.5V | 6.8 |
| GPT-4 | 6.8 |
| Gemini 2.5 Flash Lite | 6.7 |
| GPT-4o-mini | 6.7 |
| GPT-4o-mini (2024-07-18) | 6.7 |
| Granite 4.1 8B | 6.4 |
| Saba | 6.2 |
| Olmo 3 32B Think | 6.1 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.05
- Output / 1M tokens
- $0.1
- Cached input / 1M
- $0.05
- Blended 3:1
- $0.063
One task, estimated
$0.005
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.