IBMgranite-4.0-micro
granite-4.0-micro is an IBM open-weights model, released 2 Oct 2025. Its best configuration ranks #752 of 785 on the BenchLeader Index at 36.2 ±5.3, in the lower half. The ± is the point: 174 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (40) and lowest in knowledge (27). Last measured 24 Nov 2025.stale: no new result in six months
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 2 Oct 2025
- Overall index36
- Reasoning32
- Agents & tools35
- Maths32
- Knowledge27
- Instruction following40
- Long context27
- Composite35
Versions
IBM has shipped 2 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-4.0-microthis page | 2 Oct 2025 | 36.2 | #752 |
| Granite 4.0 Micro | – | – | – |
How its index has moved
9 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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 | not stated | Source |
|---|---|---|
| GPQA Diamond | 28.3%#274 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | 33.6%#502 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 5.0%#454 | Artificial Analysis |
| GPQA Diamond (HELM)not in index | 30.7%#61 | HELM Capabilities |
| CritPt | 0.0%#315 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench Hard | 1.5%#338 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 12.6%#373 | Artificial Analysis |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| OTIS Mock AIME | 2.8%#253 | Epoch AI Benchmarking Hub |
| Omni-MATH (HELM) | 20.9%#57 | HELM Capabilities |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| AA-Omniscience | -77.5#535 | Artificial Analysis |
| MMLU-Pro (HELM)not in index | 39.5%#61 | HELM Capabilities |
| AA-Omniscience: accuracynot in index | 9.3%#504 | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 4.2%#534 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| IFBench | 24.8%#394 | Artificial Analysis |
| IFEval (HELM) | 84.9%#21 | HELM Capabilities |
| WildBench (HELM) | 67.0%#63 | HELM Capabilities |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR | 7.0%#477 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2 | 5.1#604 | Artificial Analysis |
| HELM Capabilities meannot in index | 48.6%#57 | HELM Capabilities |
More from IBM
See also
Questions people ask
- What are granite-4.0-micro's benchmark scores?
- As of 25 Oct 2026, granite-4.0-micro scores 36.2 ±5.3 on the BenchLeader Index, strongest in instruction following (40) and weakest in knowledge (27). That rests on 11 independent benchmark results, and every score on this page links to its publisher.
- How does granite-4.0-micro rank?
- granite-4.0-micro is #752 of 785 ranked configurations on 25 Oct 2026. 174 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was granite-4.0-micro released?
- IBM released granite-4.0-micro on 2 Oct 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “granite-4.0-micro: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/granite-4-0-micro.