Model comparison
Magistral Medium vs o1-pro
Magistral Medium is the stronger model overall, scoring 35.2 to 31.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Magistral Medium scores higher in 1 category and o1-pro in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o1-pro leads 20.4 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 6.1% for Magistral Medium and 23.3% for o1-pro.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $150 / $600 for o1-pro.
- Magistral Medium accepts more context: 262K tokens versus 200K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | o1-pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 35.2 | 31.5 |
| Released | 2025-03-17 | 2025-03-19 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 16K | 100K |
| Input $ / M tokens | $2 | $150 |
| Output $ / M tokens | $5 | $600 |
| Results tracked | 22 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Magistral Medium: 39.1 (#161), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| SciCode | 39.2% | — |
| LMArena Coding | 1319 | — |
Reasoning o1-pro leads
Magistral Medium: 8.6 (#348), o1-pro: 20.4 (#239)
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| ARC-AGI-1 | 6.1% | 23.3% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| CritPt | 0.3% | — |
| EnigmaEval | — | 6.1% |
| LMArena Hard Prompts | 1267 | — |
Math Not comparable
Magistral Medium: 35.1 (#189), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| LMArena Math | 1250 | — |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), o1-pro: 29.7 (#234)
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Magistral Medium: 39.6 (#224), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| 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), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Magistral Medium: 39.3 (#183), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| LMArena Longer Query | 1295 | — |
Writing & Preference Not comparable
Magistral Medium: 46.3 (#219), o1-pro: —
| Benchmark | Magistral Medium | o1-pro |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |
Frequently asked questions
Is Magistral Medium better than o1-pro?
Magistral Medium is the stronger model overall, scoring 35.2 to 31.5 on the Noometry Index.
Which is cheaper, Magistral Medium or o1-pro?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; o1-pro lists at $150 and $600.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 200K.
How many benchmarks do Magistral Medium and o1-pro share?
1 benchmark has published results for both models. Magistral Medium has 22 scored results on Noometry and o1-pro has 3.