Model comparison
Granite 4.0 Micro vs Magistral Small
Magistral Small is the stronger model overall, scoring 30.2 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 18× less per token, which makes it the better buy when Magistral Small's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Granite 4.0 Micro scores higher in 1 category and Magistral Small in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Small leads 30.9 to 9.9.
- The biggest single-benchmark swing is GPQA Diamond: 28.3% for Granite 4.0 Micro and 56.1% for Magistral Small.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Granite 4.0 Micro accepts more context: 131K tokens versus 128K.
Side by side
| Granite 4.0 Micro | Magistral Small | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 29.0 | 30.2 |
| Released | 2025-10-02 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 118K | 40K |
| Input $ / M tokens | $0.017 | $0.50 |
| Output $ / M tokens | $0.11 | $1.50 |
| Results tracked | 8 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, Magistral Small: 38.4 (#176)
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| SciCode | — | 35.2% |
Reasoning Granite 4.0 Micro leads
Granite 4.0 Micro: 19.2 (#265), Magistral Small: 6.8 (#350)
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| Chess Puzzles | 0% | 3% |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |
Math Magistral Small leads
Granite 4.0 Micro: 12.0 (#307), Magistral Small: 26.2 (#261)
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 30% |
| Omni-MATH | 20.9% | — |
Knowledge Magistral Small leads
Granite 4.0 Micro: 9.9 (#304), Magistral Small: 30.9 (#223)
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| GPQA Diamond | 28.3% | 56.1% |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
Instruction Following Not comparable
Granite 4.0 Micro: 69.9 (#169), Magistral Small: —
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| IFEval | 84.9% | — |
Writing & Preference Not comparable
Granite 4.0 Micro: 46.7 (#216), Magistral Small: —
| Benchmark | Granite 4.0 Micro | Magistral Small |
|---|---|---|
| WildBench | 67% | — |
Frequently asked questions
Is Granite 4.0 Micro better than Magistral Small?
Magistral Small is the stronger model overall, scoring 30.2 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 18× less per token, which makes it the better buy when Magistral Small's lead doesn't matter for your workload.
Which is cheaper, Granite 4.0 Micro or Magistral Small?
Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Magistral Small lists at $0.50 and $1.50.
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 Magistral Small share?
3 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Magistral Small has 10.