Model comparison
Magistral Medium vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 35.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Magistral Medium scores higher in 2 categories and o3-mini in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o3-mini leads 75.1 to 66.0.
- The biggest single-benchmark swing is ARC-AGI-1: 6.1% for Magistral Medium and 34.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $5 for Magistral Medium.
- 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 | o3-mini | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 35.2 | 36.7 |
| Released | 2025-03-17 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 16K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $5 | $4.40 |
| Results tracked | 22 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Magistral Medium: 39.1 (#161), o3-mini: 40.8 (#132)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| SciCode | 39.2% | 39.8% |
| LMArena Coding | 1319 | 1378 |
| Aider Polyglot | — | 60.4% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Magistral Medium: —, o3-mini: 29.6 (#84)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Magistral Medium: 8.6 (#348), o3-mini: 16.3 (#305)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 3% |
| ARC-AGI-1 | 6.1% | 34.5% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1267 | 1366 |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 16.2% | — |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.34 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), o3-mini: 28.1 (#244)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Math | 1250 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Magistral Medium: 33.5 (#202), o3-mini: 38.3 (#146)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Expert | 1223 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
Multilingual o3-mini leads
Magistral Medium: 39.6 (#224), o3-mini: 45.7 (#164)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Non-English | 1232 | 1319 |
| LMArena Chinese | 1227 | 1379 |
| LMArena French | 1267 | 1334 |
| LMArena German | 1248 | 1303 |
| LMArena Japanese | 1175 | 1286 |
| LMArena Korean | 1125 | 1314 |
| LMArena Russian | 1224 | 1304 |
| LMArena Spanish | 1271 | 1321 |
Instruction Following o3-mini leads
Magistral Medium: 66.0 (#211), o3-mini: 75.1 (#72)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1254 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), o3-mini: 33.8 (#256)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Longer Query | 1295 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Magistral Medium: 46.3 (#219), o3-mini: 50.3 (#182)
| Benchmark | Magistral Medium | o3-mini |
|---|---|---|
| LMArena Text | 1255 | 1337 |
| LMArena Creative Writing | 1245 | 1286 |
| LMArena Multi-Turn | 1275 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Magistral Medium better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 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 o3-mini share?
21 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and o3-mini has 51.