Model comparison
MiniMax-M2.7 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. MiniMax-M2.7 scores higher in 2 categories and Qwen3.7 Plus in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 25.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 and 74.8% for Qwen3.7 Plus.
- MiniMax-M2.7 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-M2.7 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.7 | Qwen3.7 Plus | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 45.3 |
| Released | 2026-03-18 | 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 | 30 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.8 (#120), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| SciCode | 47% | 45.5% |
| LMArena Coding | 1454 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1398 | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use MiniMax-M2.7 leads
MiniMax-M2.7: 25.1 (#111), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| OSWorld 2.0 | — | 2.8% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning Qwen3.7 Plus leads
MiniMax-M2.7: 19.7 (#253), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 24.7% | 74.8% |
| CritPt | 0.6% | 9.1% |
| LMArena Hard Prompts | 1422 | 1460 |
| Epoch Capabilities Index | 145.85 | 147.37 |
| Chess Puzzles | — | 24% |
| Thematic Generalization | 39.3% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
Math Qwen3.7 Plus leads
MiniMax-M2.7: 25.9 (#263), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1420 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | 3% | — |
Knowledge Qwen3.7 Plus leads
MiniMax-M2.7: 37.7 (#152), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1444 | 1467 |
| GPQA Diamond | — | 87.9% |
| Vectara Hallucination Rate | 12.9% | — |
Multimodal Not comparable
MiniMax-M2.7: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
MiniMax-M2.7: 50.3 (#123), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1382 | 1445 |
| LMArena Chinese | 1441 | 1510 |
| LMArena French | 1421 | 1473 |
| LMArena German | 1398 | 1471 |
| LMArena Japanese | 1262 | 1413 |
| LMArena Korean | 1313 | 1415 |
| LMArena Russian | 1383 | 1457 |
| LMArena Spanish | 1403 | 1457 |
Instruction Following Qwen3.7 Plus leads
MiniMax-M2.7: 74.1 (#103), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1405 | 1440 |
Long Context Qwen3.7 Plus leads
MiniMax-M2.7: 43.3 (#99), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1419 | 1455 |
Writing & Preference Qwen3.7 Plus leads
MiniMax-M2.7: 58.9 (#112), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | MiniMax-M2.7 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1405 | 1455 |
| LMArena Creative Writing | 1354 | 1439 |
| LMArena Multi-Turn | 1412 | 1460 |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.7 on the Noometry Index.
Which is cheaper, MiniMax-M2.7 or Qwen3.7 Plus?
MiniMax-M2.7 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-M2.7 or Qwen3.7 Plus better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 36.6 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-M2.7 and Qwen3.7 Plus share?
21 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.7 Plus has 32.