Model comparison
Magistral Small vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 29.9 on the Noometry Index. Magistral Small costs 1.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
StepFunSummary
- They share 2 benchmarks with published results for both. Magistral Small scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 6.9.
- The biggest single-benchmark swing is SciCode: 35.2% for Magistral Small and 58.9% for Step 5 Preview.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| Magistral Small | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 29.9 | 43.8 |
| Released | 2025-06-10 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 40K | 66K |
| Input $ / M tokens | $0.50 | $1 |
| Output $ / M tokens | $1.50 | $2.70 |
| Results tracked | 10 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Magistral Small: 37.8 (#172), Step 5 Preview: 50.6 (#40)
| Benchmark | Magistral Small | Step 5 Preview |
|---|---|---|
| SciCode | 35.2% | 58.9% |
| LMArena WebDev | — | 1569 |
Reasoning Step 5 Preview leads
Magistral Small: 6.9 (#345), Step 5 Preview: 38.0 (#58)
| Benchmark | Magistral Small | Step 5 Preview |
|---|---|---|
| CritPt | 0.3% | 20.9% |
| 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: 24.9 (#253), Step 5 Preview: —
| Benchmark | Magistral Small | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
Knowledge Not comparable
Magistral Small: 30.9 (#215), Step 5 Preview: —
| Benchmark | Magistral Small | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 56.1% | — |
Frequently asked questions
Is Magistral Small better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 29.9 on the Noometry Index. Magistral Small costs 1.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Magistral Small or Step 5 Preview?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Magistral Small or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 128K.
How many benchmarks do Magistral Small and Step 5 Preview share?
2 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Step 5 Preview has 3.