Model comparison
MiniMax-M2 vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 7.1× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 19.4.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 85.1% for Qwen3.7 Max.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | Qwen3.7 Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 51.5 |
| Released | 2025-10-27 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.30 | $2.50 |
| Output $ / M tokens | $1.20 | $7.50 |
| Results tracked | 21 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
MiniMax-M2: 39.3 (#159), Qwen3.7 Max: 50.4 (#45)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1297 | 1515 |
| LMArena Coding | 1370 | 1498 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 61% | — |
| SciCode | — | 48.8% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use MiniMax-M2 leads
MiniMax-M2: 25.1 (#109), Qwen3.7 Max: 22.1 (#135)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| Terminal-Bench | 30% | — |
| GBAEval | — | 0.4% |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen3.7 Max leads
MiniMax-M2: 19.4 (#258), Qwen3.7 Max: 49.2 (#38)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| NYT Connections (extended) | 14.8% | 85.1% |
| LMArena Hard Prompts | 1357 | 1483 |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 57.8% | — |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.68 |
Math Qwen3.7 Max leads
MiniMax-M2: 37.3 (#160), Qwen3.7 Max: 62.4 (#32)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1352 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
Knowledge Qwen3.7 Max leads
MiniMax-M2: 37.0 (#163), Qwen3.7 Max: 61.6 (#28)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1337 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
Multilingual Qwen3.7 Max leads
MiniMax-M2: 45.3 (#171), Qwen3.7 Max: 56.9 (#15)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1313 | 1474 |
| LMArena Chinese | 1366 | 1530 |
| LMArena Russian | 1331 | 1484 |
| LMArena French | 1335 | — |
| LMArena German | 1355 | — |
| LMArena Spanish | 1326 | — |
Instruction Following Qwen3.7 Max leads
MiniMax-M2: 70.2 (#166), Qwen3.7 Max: 76.7 (#38)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1328 | 1460 |
Long Context Qwen3.7 Max leads
MiniMax-M2: 40.5 (#153), Qwen3.7 Max: 45.4 (#40)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1331 | 1482 |
Writing & Preference Qwen3.7 Max leads
MiniMax-M2: 53.0 (#162), Qwen3.7 Max: 65.0 (#54)
| Benchmark | MiniMax-M2 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1340 | 1476 |
| LMArena Creative Writing | 1286 | 1449 |
| LMArena Multi-Turn | 1361 | 1481 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is MiniMax-M2 better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 7.1× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2 or Qwen3.7 Max?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is MiniMax-M2 or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 205K.
How many benchmarks do MiniMax-M2 and Qwen3.7 Max share?
14 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3.7 Max has 33.