Model comparison
MiniMax-M2 vs Qwen Max
MiniMax-M2 is the stronger model overall, scoring 37.4 to 34.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. MiniMax-M2 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 leads 37.3 to 22.3.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- MiniMax-M2 accepts more context: 205K tokens versus 33K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | Qwen Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 34.7 |
| Released | 2025-10-27 | 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 | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Qwen Max: 30.7 (#292)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Coding | 1370 | 1288 |
| SWE-bench Verified (bash only) | 61% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1297 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Qwen Max: —
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen Max leads
MiniMax-M2: 19.4 (#258), Qwen Max: 25.1 (#151)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1269 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
Math MiniMax-M2 leads
MiniMax-M2: 37.3 (#160), Qwen Max: 22.3 (#276)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Math | 1352 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge MiniMax-M2 leads
MiniMax-M2: 37.0 (#163), Qwen Max: 30.3 (#228)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Expert | 1337 | 1248 |
| GPQA Diamond | — | 56.1% |
Multilingual MiniMax-M2 leads
MiniMax-M2: 45.3 (#171), Qwen Max: 41.8 (#202)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1313 | 1263 |
| LMArena Chinese | 1366 | 1254 |
| LMArena French | 1335 | 1330 |
| LMArena German | 1355 | 1254 |
| LMArena Russian | 1331 | 1274 |
| LMArena Spanish | 1326 | 1290 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
Instruction Following MiniMax-M2 leads
MiniMax-M2: 70.2 (#166), Qwen Max: 66.5 (#208)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1328 | 1262 |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#153), Qwen Max: 39.4 (#180)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1331 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.0 (#162), Qwen Max: 47.8 (#205)
| Benchmark | MiniMax-M2 | Qwen Max |
|---|---|---|
| LMArena Text | 1340 | 1282 |
| LMArena Creative Writing | 1286 | 1248 |
| LMArena Multi-Turn | 1361 | 1277 |
Frequently asked questions
Is MiniMax-M2 better than Qwen Max?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 34.7 on the Noometry Index.
Which is cheaper, MiniMax-M2 or Qwen Max?
MiniMax-M2 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 or Qwen Max better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 33K.
How many benchmarks do MiniMax-M2 and Qwen Max share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen Max has 23.