Model comparison
Magistral Medium vs Mistral Small 3
Magistral Medium is the stronger model overall, scoring 35.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 48× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Mistral Small 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 16.3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 33K.
Side by side
| Magistral Medium | Mistral Small 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 31.2 |
| Released | 2025-03-17 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 16K | 16K |
| Input $ / M tokens | $2 | $0.05 |
| Output $ / M tokens | $5 | $0.08 |
| Results tracked | 22 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Mistral Small 3: 36.5 (#207)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1319 | 1246 |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning Mistral Small 3 leads
Magistral Medium: 8.6 (#348), Mistral Small 3: 18.9 (#273)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1233 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Mistral Small 3: 16.3 (#295)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1250 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Mistral Small 3: 25.1 (#263)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1223 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Mistral Small 3: 37.3 (#236)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1232 | 1198 |
| LMArena Chinese | 1227 | 1204 |
| LMArena French | 1267 | 1203 |
| LMArena German | 1248 | 1211 |
| LMArena Japanese | 1175 | 1111 |
| LMArena Korean | 1125 | 1188 |
| LMArena Russian | 1224 | 1216 |
| LMArena Spanish | 1271 | — |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Mistral Small 3: 63.7 (#229)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1214 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Mistral Small 3: 37.8 (#211)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1295 | 1246 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Mistral Small 3: 32.2 (#280)
| Benchmark | Magistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1255 | 1234 |
| LMArena Creative Writing | 1245 | 1195 |
| LMArena Multi-Turn | 1275 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Magistral Medium better than Mistral Small 3?
Magistral Medium is the stronger model overall, scoring 35.2 to 31.2 on the Noometry Index. Mistral Small 3 costs 48× 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 Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Mistral Small 3 better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 33K.
How many benchmarks do Magistral Medium and Mistral Small 3 share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral Small 3 has 24.