Model comparison
MiniMax-M2.7 vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 38.6 to 37.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
MiniMax
Mistral AISummary
- They share 21 benchmarks with published results for both. MiniMax-M2.7 scores higher in 5 categories and Mistral Large 3 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 36.0 to 24.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 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-M2.7.
- Mistral Large 3 accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2.7 | Mistral Large 3 | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.4 | 38.6 |
| Released | 2026-03-18 | 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 | 30 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.4 (#115), Mistral Large 3: 34.1 (#230)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1397 | 1230 |
| LMArena Coding | 1454 | 1447 |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.7: 24.9 (#103), Mistral Large 3: —
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning MiniMax-M2.7 leads
MiniMax-M2.7: 19.0 (#248), Mistral Large 3: 14.6 (#314)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 24.7% | 7.5% |
| Thematic Generalization | 39.3% | 23% |
| LMArena Hard Prompts | 1422 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| CritPt | 0.6% | — |
| Epoch Capabilities Index | 145.84 | — |
Math Mistral Large 3 leads
MiniMax-M2.7: 24.9 (#254), Mistral Large 3: 36.0 (#131)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1420 | 1415 |
| ProofBench | 3% | — |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.1 (#151), Mistral Large 3: 35.5 (#173)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 14.5% |
| LMArena Expert | 1443 | 1421 |
Multimodal Not comparable
MiniMax-M2.7: —, Mistral Large 3: 37.6 (#65)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |
Multilingual Mistral Large 3 leads
MiniMax-M2.7: 50.5 (#120), Mistral Large 3: 52.6 (#79)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1382 | 1412 |
| LMArena Chinese | 1439 | 1448 |
| LMArena French | 1422 | 1456 |
| LMArena German | 1398 | 1438 |
| LMArena Japanese | 1261 | 1399 |
| LMArena Korean | 1313 | 1384 |
| LMArena Russian | 1383 | 1412 |
| LMArena Spanish | 1403 | 1437 |
Instruction Following Too close to call
MiniMax-M2.7: 74.2 (#101), Mistral Large 3: 74.1 (#104)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1402 |
Long Context Too close to call
MiniMax-M2.7: 43.3 (#94), Mistral Large 3: 43.1 (#102)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1419 | 1413 |
Writing & Preference Mistral Large 3 leads
MiniMax-M2.7: 59.1 (#107), Mistral Large 3: 60.2 (#100)
| Benchmark | MiniMax-M2.7 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1404 | 1427 |
| LMArena Creative Writing | 1354 | 1385 |
| LMArena Multi-Turn | 1413 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is MiniMax-M2.7 better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 38.6 to 37.4 on the Noometry Index.
Which is cheaper, MiniMax-M2.7 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-M2.7 lists at $0.30 and $1.20.
Is MiniMax-M2.7 or Mistral Large 3 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 34.1 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-M2.7 and Mistral Large 3 share?
21 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Mistral Large 3 has 24.