Model comparison
Magistral Small vs Nova 2.0 Pro Preview
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 30.2 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Magistral Small scores higher in 0 categories and Nova 2.0 Pro Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nova 2.0 Pro Preview leads 22.4 to 6.8.
- The biggest single-benchmark swing is SciCode: 35.2% for Magistral Small and 42.7% for Nova 2.0 Pro Preview.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| Magistral Small | Nova 2.0 Pro Preview | |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 30.2 | 33.4 |
| Released | 2025-06-10 | 2025-12-02 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 10 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2.0 Pro Preview leads
Magistral Small: 38.4 (#176), Nova 2.0 Pro Preview: 40.8 (#133)
| Benchmark | Magistral Small | Nova 2.0 Pro Preview |
|---|---|---|
| SciCode | 35.2% | 42.7% |
Agentic & Tool Use Not comparable
Magistral Small: —, Nova 2.0 Pro Preview: 21.9 (#136)
| Benchmark | Magistral Small | Nova 2.0 Pro Preview |
|---|---|---|
| GDP.pdf | — | 2% |
Reasoning Nova 2.0 Pro Preview leads
Magistral Small: 6.8 (#350), Nova 2.0 Pro Preview: 22.4 (#194)
| Benchmark | Magistral Small | Nova 2.0 Pro Preview |
|---|---|---|
| CritPt | 0.3% | 0% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| Chess Puzzles | 3% | — |
| DTBench | 61.3% | — |
| Epoch Capabilities Index | 133.19 | — |
Math Not comparable
Magistral Small: 26.2 (#261), Nova 2.0 Pro Preview: —
| Benchmark | Magistral Small | Nova 2.0 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
Knowledge Not comparable
Magistral Small: 30.9 (#223), Nova 2.0 Pro Preview: —
| Benchmark | Magistral Small | Nova 2.0 Pro Preview |
|---|---|---|
| GPQA Diamond | 56.1% | — |
Frequently asked questions
Is Magistral Small better than Nova 2.0 Pro Preview?
Nova 2.0 Pro Preview is the stronger model overall, scoring 33.4 to 30.2 on the Noometry Index.
Is Magistral Small or Nova 2.0 Pro Preview better for coding?
Nova 2.0 Pro Preview scores higher on coding benchmarks: 40.8 versus 38.4 in the Noometry coding category.
How many benchmarks do Magistral Small and Nova 2.0 Pro Preview share?
2 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Nova 2.0 Pro Preview has 3.