Model comparison
Magistral Medium vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 35.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Magistral Medium scores higher in 3 categories and Mistral Medium in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Medium leads 24.0 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 50% for Mistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Magistral Medium | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 36.3 |
| Released | 2025-03-17 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 262K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $5 | $7.50 |
| Results tracked | 22 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| SciCode | 39.2% | 40.2% |
| LMArena Coding | 1319 | 1434 |
| FrontierCode | — | 8% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
Magistral Medium: —, Mistral Medium: 28.3 (#90)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Magistral Medium: 8.6 (#348), Mistral Medium: 24.0 (#167)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 50% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1267 | 1426 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Mistral Medium: 28.1 (#245)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Math | 1250 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Mistral Medium: 25.0 (#265)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Expert | 1223 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
Magistral Medium: —, Mistral Medium: 35.3 (#88)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Magistral Medium: 39.6 (#224), Mistral Medium: 52.1 (#91)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1232 | 1408 |
| LMArena Chinese | 1227 | 1447 |
| LMArena French | 1267 | 1459 |
| LMArena German | 1248 | 1432 |
| LMArena Japanese | 1175 | 1378 |
| LMArena Korean | 1125 | 1380 |
| LMArena Russian | 1224 | 1411 |
| LMArena Spanish | 1271 | 1433 |
Instruction Following Mistral Medium leads
Magistral Medium: 66.0 (#211), Mistral Medium: 73.7 (#116)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1254 | 1398 |
Long Context Mistral Medium leads
Magistral Medium: 39.3 (#183), Mistral Medium: 42.9 (#114)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1295 | 1406 |
Writing & Preference Mistral Medium leads
Magistral Medium: 46.3 (#219), Mistral Medium: 60.0 (#103)
| Benchmark | Magistral Medium | Mistral Medium |
|---|---|---|
| LMArena Text | 1255 | 1424 |
| LMArena Creative Writing | 1245 | 1391 |
| LMArena Multi-Turn | 1275 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Magistral Medium better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Mistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Magistral Medium or Mistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Magistral Medium and Mistral Medium share?
20 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral Medium has 36.