Model comparison
MiniMax-M2 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 36.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 2 categories and Qwen3.7 Plus in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 38.4 to 18.6.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 74.8% for Qwen3.7 Plus.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus 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 Plus | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 36.9 | 45.0 |
| Released | 2025-10-27 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $1.20 | $1.60 |
| Results tracked | 21 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.1 (#151), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1370 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| SciCode | — | 45.5% |
Agentic & Tool Use MiniMax-M2 leads
MiniMax-M2: 24.9 (#102), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 30% | — |
| OSWorld 2.0 | — | 2.8% |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen3.7 Plus leads
MiniMax-M2: 18.6 (#256), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 14.8% | 74.8% |
| LMArena Hard Prompts | 1357 | 1460 |
| Kagi LLM Benchmark | 57.8% | — |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.39 |
Math Qwen3.7 Plus leads
MiniMax-M2: 34.6 (#158), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1350 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
Knowledge Qwen3.7 Plus leads
MiniMax-M2: 36.3 (#160), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1336 | 1467 |
| GPQA Diamond | — | 87.9% |
Multimodal Not comparable
MiniMax-M2: —, Qwen3.7 Plus: 41.2 (#30)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
MiniMax-M2: 45.6 (#165), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1314 | 1445 |
| LMArena Chinese | 1367 | 1510 |
| LMArena French | 1336 | 1471 |
| LMArena German | 1366 | 1471 |
| LMArena Russian | 1332 | 1457 |
| LMArena Spanish | 1326 | 1453 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1416 |
Instruction Following Qwen3.7 Plus leads
MiniMax-M2: 70.4 (#160), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1329 | 1439 |
Long Context Qwen3.7 Plus leads
MiniMax-M2: 40.5 (#148), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1332 | 1454 |
Writing & Preference Qwen3.7 Plus leads
MiniMax-M2: 53.3 (#157), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | MiniMax-M2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1340 | 1454 |
| LMArena Creative Writing | 1288 | 1439 |
| LMArena Multi-Turn | 1362 | 1459 |
Frequently asked questions
Is MiniMax-M2 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 36.9 on the Noometry Index.
Which is cheaper, MiniMax-M2 or Qwen3.7 Plus?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is MiniMax-M2 or Qwen3.7 Plus better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 205K.
How many benchmarks do MiniMax-M2 and Qwen3.7 Plus share?
16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3.7 Plus has 32.