Model comparison
MiniMax-M2 vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 37.4 on the Noometry Index. MiniMax-M2 costs 4.6× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 37.0.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 30.1% for Qwen3 Max.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | Qwen3 Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 43.7 |
| Released | 2025-10-27 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $1.20 |
| Output $ / M tokens | $1.20 | $6 |
| Results tracked | 21 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
MiniMax-M2: 39.3 (#159), Qwen3 Max: 43.0 (#93)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1370 | 1456 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Qwen3 Max: —
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 160.6 | 71.56 |
| Terminal-Bench | 30% | — |
Reasoning Qwen3 Max leads
MiniMax-M2: 19.4 (#258), Qwen3 Max: 22.6 (#190)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 72.5% |
| NYT Connections (extended) | 14.8% | 30.1% |
| LMArena Hard Prompts | 1357 | 1448 |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.38 |
Math Qwen3 Max leads
MiniMax-M2: 37.3 (#160), Qwen3 Max: 38.7 (#131)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Math | 1352 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
MiniMax-M2: 37.0 (#163), Qwen3 Max: 48.1 (#78)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1337 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
Multilingual Qwen3 Max leads
MiniMax-M2: 45.3 (#171), Qwen3 Max: 53.7 (#62)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1313 | 1429 |
| LMArena Chinese | 1366 | 1478 |
| LMArena French | 1335 | 1449 |
| LMArena German | 1355 | 1463 |
| LMArena Russian | 1331 | 1428 |
| LMArena Spanish | 1326 | 1462 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1399 |
Instruction Following Qwen3 Max leads
MiniMax-M2: 70.2 (#166), Qwen3 Max: 74.8 (#87)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1328 | 1419 |
Long Context Qwen3 Max leads
MiniMax-M2: 40.5 (#153), Qwen3 Max: 41.6 (#134)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1331 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
MiniMax-M2: 53.0 (#162), Qwen3 Max: 62.4 (#76)
| Benchmark | MiniMax-M2 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1340 | 1439 |
| LMArena Creative Writing | 1286 | 1402 |
| LMArena Multi-Turn | 1361 | 1446 |
Frequently asked questions
Is MiniMax-M2 better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 37.4 on the Noometry Index. MiniMax-M2 costs 4.6× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2 or Qwen3 Max?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is MiniMax-M2 or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2 and Qwen3 Max share?
18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3 Max has 33.