Model comparison
Magistral Medium vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 35.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
MiniMaxSummary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and MiniMax-M2 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiniMax-M2 leads 19.4 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 57.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 205K.
Side by side
| Magistral Medium | MiniMax-M2 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 35.2 | 37.4 |
| Released | 2025-03-17 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $5 | $1.20 |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Medium: 39.1 (#161), MiniMax-M2: 39.3 (#159)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1319 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| SciCode | 39.2% | — |
Agentic & Tool Use Not comparable
Magistral Medium: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Magistral Medium: 8.6 (#348), MiniMax-M2: 19.4 (#258)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 57.8% |
| LMArena Hard Prompts | 1267 | 1357 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math MiniMax-M2 leads
Magistral Medium: 35.1 (#189), MiniMax-M2: 37.3 (#160)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1250 | 1352 |
Knowledge MiniMax-M2 leads
Magistral Medium: 33.5 (#202), MiniMax-M2: 37.0 (#163)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1223 | 1337 |
Multilingual MiniMax-M2 leads
Magistral Medium: 39.6 (#224), MiniMax-M2: 45.3 (#171)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1232 | 1313 |
| LMArena Chinese | 1227 | 1366 |
| LMArena French | 1267 | 1335 |
| LMArena German | 1248 | 1355 |
| LMArena Russian | 1224 | 1331 |
| LMArena Spanish | 1271 | 1326 |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
Instruction Following MiniMax-M2 leads
Magistral Medium: 66.0 (#211), MiniMax-M2: 70.2 (#166)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1328 |
Long Context MiniMax-M2 leads
Magistral Medium: 39.3 (#183), MiniMax-M2: 40.5 (#153)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1295 | 1331 |
Writing & Preference MiniMax-M2 leads
Magistral Medium: 46.3 (#219), MiniMax-M2: 53.0 (#162)
| Benchmark | Magistral Medium | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1255 | 1340 |
| LMArena Creative Writing | 1245 | 1286 |
| LMArena Multi-Turn | 1275 | 1361 |
Frequently asked questions
Is Magistral Medium better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or MiniMax-M2?
MiniMax-M2 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-M2 better for coding?
They score almost the same on coding (39.1 vs 39.3); test both on your own repository before choosing.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 205K.
How many benchmarks do Magistral Medium and MiniMax-M2 share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and MiniMax-M2 has 21.