Model comparison
Granite 4.0 Micro vs Ministral 3B
Granite 4.0 Micro is the stronger model overall, scoring 28.8 to 25.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Granite 4.0 Micro scores higher in 1 category and Ministral 3B in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 24.5 to 11.2.
- Both cost about the same: $0.017 input and $0.11 output per million tokens.
- Granite 4.0 Micro accepts more context: 131K tokens versus 128K.
Side by side
| Granite 4.0 Micro | Ministral 3B | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 28.8 | 25.6 |
| Released | 2025-10-02 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 118K | 128K |
| Input $ / M tokens | $0.017 | $0.04 |
| Output $ / M tokens | $0.11 | $0.04 |
| Results tracked | 8 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Reasoning Too close to call
Granite 4.0 Micro: 18.5 (#261), Ministral 3B: 17.7 (#278)
| Benchmark | Granite 4.0 Micro | Ministral 3B |
|---|---|---|
| Chess Puzzles | 0% | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 118.08 |
Math Ministral 3B leads
Granite 4.0 Micro: 11.2 (#301), Ministral 3B: 24.5 (#257)
| Benchmark | Granite 4.0 Micro | Ministral 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |
| MATH Level 5 | — | 14.4% |
Knowledge Too close to call
Granite 4.0 Micro: 9.9 (#299), Ministral 3B: 10.4 (#297)
| Benchmark | Granite 4.0 Micro | Ministral 3B |
|---|---|---|
| GPQA Diamond | 28.3% | 25.3% |
| MMLU-Pro | 39.5% | — |
| Vectara Hallucination Rate | — | 7.3% |
| GPQA (HELM) | 30.7% | — |
Instruction Following Not comparable
Granite 4.0 Micro: 70.0 (#164), Ministral 3B: —
| Benchmark | Granite 4.0 Micro | Ministral 3B |
|---|---|---|
| IFEval | 84.9% | — |
Writing & Preference Not comparable
Granite 4.0 Micro: 46.7 (#212), Ministral 3B: —
| Benchmark | Granite 4.0 Micro | Ministral 3B |
|---|---|---|
| WildBench | 67% | — |
Frequently asked questions
Is Granite 4.0 Micro better than Ministral 3B?
Granite 4.0 Micro is the stronger model overall, scoring 28.8 to 25.6 on the Noometry Index.
Which is cheaper, Granite 4.0 Micro or Ministral 3B?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Granite 4.0 Micro lists at $0.017 and $0.11.
Which has the bigger context window?
Granite 4.0 Micro does, with 131K tokens against 128K.
How many benchmarks do Granite 4.0 Micro and Ministral 3B share?
1 benchmark has published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Ministral 3B has 6.