Model comparison
Magistral Medium vs Magistral Small
Magistral Medium is the stronger model overall, scoring 35.2 to 30.2 on the Noometry Index. Magistral Small costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Mistral AISummary
- They share 5 benchmarks with published results for both. Magistral Medium scores higher in 4 categories and Magistral Small in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 26.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 6.3% for Magistral Small.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Magistral Medium | Magistral Small | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 30.2 |
| Released | 2025-03-17 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 16K | 40K |
| Input $ / M tokens | $2 | $0.50 |
| Output $ / M tokens | $5 | $1.50 |
| Results tracked | 22 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Medium: 39.1 (#161), Magistral Small: 38.4 (#176)
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| SciCode | 39.2% | 35.2% |
| LMArena Coding | 1319 | — |
Reasoning Magistral Medium leads
Magistral Medium: 8.6 (#348), Magistral Small: 6.8 (#350)
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 16.2% | 6.3% |
| ARC-AGI-1 | 6.1% | 5% |
| CritPt | 0.3% | 0.3% |
| Chess Puzzles | — | 3% |
| LMArena Hard Prompts | 1267 | — |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Magistral Small: 26.2 (#261)
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
| LMArena Math | 1250 | — |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Magistral Small: 30.9 (#223)
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Magistral Medium: 39.6 (#224), Magistral Small: —
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| LMArena Non-English | 1232 | — |
| LMArena Chinese | 1227 | — |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Not comparable
Magistral Medium: 66.0 (#211), Magistral Small: —
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Magistral Medium: 39.3 (#183), Magistral Small: —
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1295 | — |
Writing & Preference Not comparable
Magistral Medium: 46.3 (#219), Magistral Small: —
| Benchmark | Magistral Medium | Magistral Small |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |
Frequently asked questions
Is Magistral Medium better than Magistral Small?
Magistral Medium is the stronger model overall, scoring 35.2 to 30.2 on the Noometry Index. Magistral Small costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Magistral Medium or Magistral Small?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Magistral Small better for coding?
They score almost the same on coding (39.1 vs 38.4); test both on your own repository before choosing.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 128K.
How many benchmarks do Magistral Medium and Magistral Small share?
5 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Magistral Small has 10.