Model comparison
MiniMax-M2.1 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 38.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 0 categories and Qwen3.5 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 29.6 to 15.8.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.1 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.4 | 44.7 |
| Released | 2025-12-23 | — |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
MiniMax-M2.1: 40.1 (#132), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1421 | 1488 |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.7 (#91), Qwen3.5 Max Preview: —
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Qwen3.5 Max Preview leads
MiniMax-M2.1: 15.8 (#301), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1410 | 1483 |
| NYT Connections (extended) | 11.2% | — |
Math Qwen3.5 Max Preview leads
MiniMax-M2.1: 35.6 (#142), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1396 | 1473 |
Knowledge Qwen3.5 Max Preview leads
MiniMax-M2.1: 37.7 (#143), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1432 | 1489 |
| Vectara Hallucination Rate | 11.8% | — |
Multilingual Qwen3.5 Max Preview leads
MiniMax-M2.1: 50.2 (#123), Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1378 | 1465 |
| LMArena Chinese | 1430 | 1534 |
| LMArena French | 1405 | 1483 |
| LMArena German | 1380 | 1487 |
| LMArena Japanese | 1287 | 1497 |
| LMArena Korean | 1297 | 1438 |
| LMArena Russian | 1386 | 1472 |
| LMArena Spanish | 1396 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
MiniMax-M2.1: 74.0 (#108), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1399 | 1467 |
Long Context Qwen3.5 Max Preview leads
MiniMax-M2.1: 43.2 (#98), Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1416 | 1477 |
Writing & Preference Qwen3.5 Max Preview leads
MiniMax-M2.1: 58.5 (#114), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | MiniMax-M2.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1392 | 1471 |
| LMArena Creative Writing | 1362 | 1464 |
| LMArena Multi-Turn | 1396 | 1478 |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 38.4 on the Noometry Index.
Is MiniMax-M2.1 or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 40.1 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen3.5 Max Preview has 17.