Model comparison
MiniMax-M2.1 vs Qwen Max
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 34.7 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 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 22.3.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- MiniMax-M2.1 accepts more context: 205K tokens versus 33K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.1 | Qwen Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 34.7 |
| Released | 2025-12-23 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 205K | 33K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $1.60 |
| Output $ / M tokens | $1.20 | $6.40 |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), Qwen Max: 30.7 (#292)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Coding | 1421 | 1288 |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Qwen Max: —
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Qwen Max leads
MiniMax-M2.1: 16.6 (#302), Qwen Max: 25.1 (#151)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1269 |
| NYT Connections (extended) | 11.2% | — |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen Max: 22.3 (#276)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Math | 1397 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen Max: 30.3 (#228)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Expert | 1431 | 1248 |
| GPQA Diamond | — | 56.1% |
| Vectara Hallucination Rate | 11.8% | — |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen Max: 41.8 (#202)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1378 | 1263 |
| LMArena Chinese | 1430 | 1254 |
| LMArena French | 1404 | 1330 |
| LMArena German | 1381 | 1254 |
| LMArena Japanese | 1287 | 1205 |
| LMArena Korean | 1298 | 1142 |
| LMArena Russian | 1387 | 1274 |
| LMArena Spanish | 1397 | 1290 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen Max: 66.5 (#208)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1400 | 1262 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen Max: 39.4 (#180)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1416 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen Max: 47.8 (#205)
| Benchmark | MiniMax-M2.1 | Qwen Max |
|---|---|---|
| LMArena Text | 1392 | 1282 |
| LMArena Creative Writing | 1361 | 1248 |
| LMArena Multi-Turn | 1396 | 1277 |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen Max?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 34.7 on the Noometry Index.
Which is cheaper, MiniMax-M2.1 or Qwen Max?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is MiniMax-M2.1 or Qwen Max better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 33K.
How many benchmarks do MiniMax-M2.1 and Qwen Max share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen Max has 23.