Model comparison
MiniMax-M2 vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMax
Mistral AISummary
- They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 3 categories and Mistral Large 3 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Large 3 leads 52.5 to 45.3.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- Mistral Large 3 accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2 | Mistral Large 3 | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.4 | 39.1 |
| Released | 2025-10-27 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $1.20 | $0.75 |
| Results tracked | 21 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Mistral Large 3: 34.4 (#237)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1297 | 1230 |
| LMArena Coding | 1370 | 1448 |
| SWE-bench Verified (bash only) | 61% | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Mistral Large 3: —
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning MiniMax-M2 leads
MiniMax-M2: 19.4 (#258), Mistral Large 3: 15.2 (#319)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 50.9% |
| NYT Connections (extended) | 14.8% | 7.5% |
| LMArena Hard Prompts | 1357 | 1429 |
| Thematic Generalization | — | 23% |
Math Mistral Large 3 leads
MiniMax-M2: 37.3 (#160), Mistral Large 3: 38.7 (#129)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1352 | 1414 |
Knowledge Too close to call
MiniMax-M2: 37.0 (#163), Mistral Large 3: 36.0 (#177)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1337 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Not comparable
MiniMax-M2: —, Mistral Large 3: 38.2 (#66)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
MiniMax-M2: 45.3 (#171), Mistral Large 3: 52.5 (#84)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1313 | 1413 |
| LMArena Chinese | 1366 | 1447 |
| LMArena French | 1335 | 1455 |
| LMArena German | 1355 | 1437 |
| LMArena Russian | 1331 | 1411 |
| LMArena Spanish | 1326 | 1440 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
Instruction Following Mistral Large 3 leads
MiniMax-M2: 70.2 (#166), Mistral Large 3: 74.0 (#108)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1328 | 1403 |
Long Context Mistral Large 3 leads
MiniMax-M2: 40.5 (#153), Mistral Large 3: 43.1 (#105)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1331 | 1413 |
Writing & Preference Mistral Large 3 leads
MiniMax-M2: 53.0 (#162), Mistral Large 3: 60.0 (#101)
| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1340 | 1428 |
| LMArena Creative Writing | 1286 | 1386 |
| LMArena Multi-Turn | 1361 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is MiniMax-M2 better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.
Which is cheaper, MiniMax-M2 or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is MiniMax-M2 or Mistral Large 3 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2 and Mistral Large 3 share?
18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Mistral Large 3 has 24.