Model comparison
Devstral Small 2505 vs Magistral Medium
Devstral Small 2505 and Magistral Medium score almost the same on the Noometry Index (34.3 vs 35.2), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and Magistral Medium in 1 category; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Devstral Small 2505 leads 19.7 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 16.2% for Magistral Medium.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 34.3 | 35.2 |
| Released | 2025-05-07 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.30 | $5 |
| Results tracked | 4 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.9 (#166), Magistral Medium: 39.1 (#161)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| SciCode | 28.8% | 39.2% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena Coding | — | 1319 |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), Magistral Medium: 8.6 (#348)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 16.2% |
| CritPt | 0% | 0.3% |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| LMArena Hard Prompts | — | 1267 |
Math Not comparable
Devstral Small 2505: —, Magistral Medium: 35.1 (#189)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| LMArena Math | — | 1250 |
Knowledge Not comparable
Devstral Small 2505: —, Magistral Medium: 33.5 (#202)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| LMArena Expert | — | 1223 |
Multilingual Not comparable
Devstral Small 2505: —, Magistral Medium: 39.6 (#224)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| 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
Devstral Small 2505: —, Magistral Medium: 66.0 (#211)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Devstral Small 2505: —, Magistral Medium: 39.3 (#183)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |
Writing & Preference Not comparable
Devstral Small 2505: —, Magistral Medium: 46.3 (#219)
| Benchmark | Devstral Small 2505 | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |
Frequently asked questions
Is Devstral Small 2505 better than Magistral Medium?
Devstral Small 2505 and Magistral Medium score almost the same on the Noometry Index (34.3 vs 35.2), so choose on price, context window or the category you care about most.
Which is cheaper, Devstral Small 2505 or Magistral Medium?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Magistral Medium lists at $2 and $5.
Is Devstral Small 2505 or Magistral Medium better for coding?
They score almost the same on coding (38.9 vs 39.1); 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 Devstral Small 2505 and Magistral Medium share?
3 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Magistral Medium has 22.