Model comparison
Magistral Medium vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 35.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AI
MiniMaxSummary
- They share 19 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 33.5.
- The biggest single-benchmark swing is SciCode: 39.2% for Magistral Medium and 47.1% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.
Side by side
| Magistral Medium | MiniMax-M3 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 35.2 | 43.8 |
| Released | 2025-03-17 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 262K | 1M |
| Max output | 16K | 512K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $5 | $1.20 |
| Results tracked | 22 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Magistral Medium: 39.1 (#161), MiniMax-M3: 41.8 (#118)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| SciCode | 39.2% | 47.1% |
| LMArena Coding | 1319 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
Magistral Medium: —, MiniMax-M3: 22.6 (#130)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Magistral Medium: 8.6 (#348), MiniMax-M3: 30.1 (#87)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| CritPt | 0.3% | 3.7% |
| LMArena Hard Prompts | 1267 | 1447 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 6.1% | — |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |
Math MiniMax-M3 leads
Magistral Medium: 35.1 (#189), MiniMax-M3: 40.0 (#95)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1250 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
Knowledge MiniMax-M3 leads
Magistral Medium: 33.5 (#202), MiniMax-M3: 58.4 (#35)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1223 | 1461 |
| GPQA Diamond | — | 90.9% |
Multimodal Not comparable
Magistral Medium: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Magistral Medium: 39.6 (#224), MiniMax-M3: 53.0 (#75)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1232 | 1420 |
| LMArena Chinese | 1227 | 1463 |
| LMArena French | 1267 | 1447 |
| LMArena German | 1248 | 1426 |
| LMArena Japanese | 1175 | 1381 |
| LMArena Korean | 1125 | 1372 |
| LMArena Russian | 1224 | 1428 |
| LMArena Spanish | 1271 | 1432 |
Instruction Following MiniMax-M3 leads
Magistral Medium: 66.0 (#211), MiniMax-M3: 75.5 (#62)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1433 |
Long Context MiniMax-M3 leads
Magistral Medium: 39.3 (#183), MiniMax-M3: 44.2 (#72)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1295 | 1445 |
Writing & Preference MiniMax-M3 leads
Magistral Medium: 46.3 (#219), MiniMax-M3: 62.1 (#83)
| Benchmark | Magistral Medium | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1255 | 1433 |
| LMArena Creative Writing | 1245 | 1404 |
| LMArena Multi-Turn | 1275 | 1442 |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Magistral Medium better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 262K.
How many benchmarks do Magistral Medium and MiniMax-M3 share?
19 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and MiniMax-M3 has 41.