Model comparison
Qwen3.7 Max vs Qwen3.7 Plus
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.4× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Qwen3.7 Max scores higher in 9 categories and Qwen3.7 Plus in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3.7 Max leads 50.4 to 36.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 64.6% for Qwen3.7 Max and 34.4% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
Side by side
| Qwen3.7 Max | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 51.5 | 45.3 |
| Released | 2026-05-19 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $2.50 | $0.40 |
| Output $ / M tokens | $7.50 | $1.60 |
| Results tracked | 33 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3.7 Max: 50.4 (#45), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| SciCode | 48.8% | 45.5% |
| LMArena Coding | 1498 | 1473 |
| SWE-bench Verified | 77.3% | — |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1515 | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Too close to call
Qwen3.7 Max: 22.1 (#135), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| GBAEval | 0.4% | — |
Reasoning Qwen3.7 Max leads
Qwen3.7 Max: 49.2 (#38), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 85.1% | 74.8% |
| CritPt | 13.4% | 9.1% |
| Chess Puzzles | 19% | 24% |
| LMArena Hard Prompts | 1483 | 1460 |
| Mystery Game Puzzles | 32% | 17% |
| DTBench | 92.3% | 84% |
| LMCA | 44% | 37.6% |
| Epoch Capabilities Index | 153.68 | 147.37 |
| SimpleBench | 70.4% | — |
| EBR-Bench | 9.5% | — |
Math Qwen3.7 Max leads
Qwen3.7 Max: 62.4 (#32), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | 34.4% |
| OTIS Mock AIME 2024-2025 | 95.6% | 93.3% |
| LMArena Math | 1490 | 1466 |
| FrontierMath Tier 4 | 34.1% | — |
| ProofBench | 26% | — |
Knowledge Qwen3.7 Max leads
Qwen3.7 Max: 61.6 (#28), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 90.9% | 87.9% |
| LMArena Expert | 1488 | 1467 |
| SimpleQA Verified | 55.8% | — |
Multimodal Not comparable
Qwen3.7 Max: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Max leads
Qwen3.7 Max: 56.9 (#15), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1474 | 1445 |
| LMArena Chinese | 1530 | 1510 |
| LMArena Russian | 1484 | 1457 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Spanish | — | 1457 |
Instruction Following Too close to call
Qwen3.7 Max: 76.7 (#38), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1460 | 1440 |
Long Context Too close to call
Qwen3.7 Max: 45.4 (#40), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1482 | 1455 |
Writing & Preference Too close to call
Qwen3.7 Max: 65.0 (#54), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen3.7 Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1476 | 1455 |
| LMArena Creative Writing | 1449 | 1439 |
| LMArena Multi-Turn | 1481 | 1460 |
| EQ-Bench 4 | 1110 | — |
Frequently asked questions
Is Qwen3.7 Max better than Qwen3.7 Plus?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.4× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.7 Max or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Qwen3.7 Max or Qwen3.7 Plus better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 36.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Qwen3.7 Max and Qwen3.7 Plus share?
23 benchmarks have published results for both models. Qwen3.7 Max has 33 scored results on Noometry and Qwen3.7 Plus has 32.