IBMGranite 3.3 8B
Granite 3.3 8B is an IBM proprietary model. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories. Last measured 24 Nov 2025.stale: no new result in six months
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Released
- –
- date not published by our sources
- Maths32
- Instruction following36
Versions
IBM has shipped 6 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Granite 4.2 8B | 25 Aug 2026 | 48.5 | #334 |
| Granite 4.1 8B | 29 Apr 2026 | 41.0 | #510 |
| Granite 3.1 8B | – | – | – |
| Granite 3.0 8B | – | – | – |
| Granite 3.3 8Bthis page | – | – | – |
| Granite 3.2 8B | – | – | – |
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 (HELM)not in index | 32.5%#58 | HELM Capabilities |
Maths
| Benchmark | default | Source |
|---|---|---|
| Omni-MATH (HELM) | 17.6%#58 | HELM Capabilities |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| MMLU-Pro (HELM)not in index | 34.3%#62 | HELM Capabilities |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFEval (HELM) | 72.9%#62 | HELM Capabilities |
| WildBench (HELM) | 74.1%#53 | HELM Capabilities |
Composite
| Benchmark | default | Source |
|---|---|---|
| HELM Capabilities meannot in index | 46.3%#61 | HELM Capabilities |
See also
Data as of 12 Sept 2026. Compare with another model.
Cite as: BenchLeader, “Granite 3.3 8B: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/granite-3-3-8b, data as of 12 Sept 2026.