Model comparison
Magistral Medium vs o1
o1 is the stronger model overall, scoring 40.9 to 35.2 on the Noometry Index. Magistral Medium costs 9.5× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o1 leads 27.9 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 6.1% for Magistral Medium and 30.7% for o1.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $15 / $60 for o1.
- 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 | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 35.2 | 40.9 |
| Released | 2025-03-17 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 16K | 100K |
| Input $ / M tokens | $2 | $15 |
| Output $ / M tokens | $5 | $60 |
| Results tracked | 22 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Magistral Medium: 39.1 (#161), o1: 46.1 (#70)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Coding | 1319 | 1367 |
| Aider Polyglot | — | 61.7% |
| SciCode | 39.2% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Magistral Medium: —, o1: 24.6 (#117)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Magistral Medium: 8.6 (#348), o1: 27.9 (#111)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| ARC-AGI-1 | 6.1% | 30.7% |
| LMArena Hard Prompts | 1267 | 1371 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 16.2% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.91 |
| LiveBench | — | 75.7% |
Math o1 leads
Magistral Medium: 35.1 (#189), o1: 36.1 (#175)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Math | 1250 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Magistral Medium: 33.5 (#202), o1: 41.5 (#110)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Expert | 1223 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
Magistral Medium: —, o1: 34.2 (#93)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Magistral Medium: 39.6 (#224), o1: 48.6 (#142)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Non-English | 1232 | 1358 |
| LMArena Chinese | 1227 | 1394 |
| LMArena French | 1267 | 1344 |
| LMArena German | 1248 | 1337 |
| LMArena Japanese | 1175 | 1346 |
| LMArena Korean | 1125 | 1396 |
| LMArena Russian | 1224 | 1356 |
| LMArena Spanish | 1271 | 1345 |
Instruction Following o1 leads
Magistral Medium: 66.0 (#211), o1: 74.8 (#86)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Magistral Medium: 39.3 (#183), o1: 50.3 (#9)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Longer Query | 1295 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Magistral Medium: 46.3 (#219), o1: 55.6 (#144)
| Benchmark | Magistral Medium | o1 |
|---|---|---|
| LMArena Text | 1255 | 1366 |
| LMArena Creative Writing | 1245 | 1348 |
| LMArena Multi-Turn | 1275 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Magistral Medium better than o1?
o1 is the stronger model overall, scoring 40.9 to 35.2 on the Noometry Index. Magistral Medium costs 9.5× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Magistral Medium or o1?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; o1 lists at $15 and $60.
Is Magistral Medium or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 200K.
How many benchmarks do Magistral Medium and o1 share?
18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and o1 has 52.