Model comparison
MiniMax-M3 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 43.8 on the Noometry Index.
Last verified . 31 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 31 benchmarks with published results for both. MiniMax-M3 scores higher in 3 categories and Qwen3.7 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 40.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 93.3% for Qwen3.7 Plus.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Qwen3.7 Plus | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 45.3 |
| Released | 2026-06-01 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 512K | 131K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $1.20 | $1.60 |
| Results tracked | 41 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 14.7% | 10.2% |
| SciCode | 47.1% | 45.5% |
| LMArena Coding | 1469 | 1473 |
| LMArena WebDev | 1482 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use MiniMax-M3 leads
MiniMax-M3: 22.6 (#130), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | 4.6% | 2.8% |
| APEX-Agents | 37.7% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning Qwen3.7 Plus leads
MiniMax-M3: 30.1 (#87), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 65.1% | 74.8% |
| CritPt | 3.7% | 9.1% |
| Chess Puzzles | 14% | 24% |
| LMArena Hard Prompts | 1447 | 1460 |
| Mystery Game Puzzles | 8% | 17% |
| DTBench | 78.9% | 84% |
| LMCA | 33.7% | 37.6% |
| Epoch Capabilities Index | 146.95 | 147.37 |
| SimpleBench | 45.8% | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |
Math Qwen3.7 Plus leads
MiniMax-M3: 40.0 (#95), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 93.3% |
| LMArena Math | 1429 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 90.9% | 87.9% |
| LMArena Expert | 1461 | 1467 |
Multimodal Qwen3.7 Plus leads
MiniMax-M3: 40.2 (#51), Qwen3.7 Plus: 41.8 (#33)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1253 | 1279 |
| LMArena Document | 1435 | 1444 |
Multilingual Qwen3.7 Plus leads
MiniMax-M3: 53.0 (#75), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1420 | 1445 |
| LMArena Chinese | 1463 | 1510 |
| LMArena French | 1447 | 1473 |
| LMArena German | 1426 | 1471 |
| LMArena Japanese | 1381 | 1413 |
| LMArena Korean | 1372 | 1415 |
| LMArena Russian | 1428 | 1457 |
| LMArena Spanish | 1432 | 1457 |
Instruction Following Too close to call
MiniMax-M3: 75.5 (#62), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1433 | 1440 |
Long Context Too close to call
MiniMax-M3: 44.2 (#72), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1445 | 1455 |
Writing & Preference Qwen3.7 Plus leads
MiniMax-M3: 62.1 (#83), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1433 | 1455 |
| LMArena Creative Writing | 1404 | 1439 |
| LMArena Multi-Turn | 1442 | 1460 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 43.8 on the Noometry Index.
Which is cheaper, MiniMax-M3 or Qwen3.7 Plus?
MiniMax-M3 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-M3 or Qwen3.7 Plus better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do MiniMax-M3 and Qwen3.7 Plus share?
31 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3.7 Plus has 32.