Model comparison
Qwen2.5-Max vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 40.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen2.5-Max scores higher in 1 category and Qwen3.7 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 35.3.
Side by side
| Qwen2.5-Max | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 45.3 |
| Released | 2025-01-25 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 27 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Qwen2.5-Max: 41.8 (#117), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1359 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| LiveBench Coding | 64.4% | — |
Agentic & Tool Use Not comparable
Qwen2.5-Max: —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Qwen2.5-Max: 25.6 (#147), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1460 |
| Epoch Capabilities Index | 132.53 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| LiveBench Reasoning | 51.4% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LiveBench Data Analysis | 67.9% | — |
| LMCA | — | 37.6% |
| LiveBench | 62.3% | — |
Math Qwen3.7 Plus leads
Qwen2.5-Max: 36.9 (#162), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1369 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| LiveBench Math | 58.4% | — |
Knowledge Qwen3.7 Plus leads
Qwen2.5-Max: 35.3 (#186), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1337 | 1467 |
| GPQA Diamond | — | 87.9% |
| Confabulations | 21.8% | — |
Multimodal Not comparable
Qwen2.5-Max: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Qwen2.5-Max: 48.1 (#146), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1352 | 1445 |
| LMArena Chinese | 1382 | 1510 |
| LMArena French | 1396 | 1473 |
| LMArena German | 1350 | 1471 |
| LMArena Japanese | 1300 | 1413 |
| LMArena Korean | 1304 | 1415 |
| LMArena Russian | 1353 | 1457 |
| LMArena Spanish | 1377 | 1457 |
Instruction Following Qwen3.7 Plus leads
Qwen2.5-Max: 71.3 (#152), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1335 | 1440 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Qwen3.7 Plus leads
Qwen2.5-Max: 41.4 (#142), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1358 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Qwen2.5-Max: 55.4 (#146), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen2.5-Max | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1367 | 1455 |
| LMArena Creative Writing | 1339 | 1439 |
| LMArena Multi-Turn | 1364 | 1460 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 40.7 on the Noometry Index.
Is Qwen2.5-Max or Qwen3.7 Plus better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 36.6 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Qwen3.7 Plus share?
18 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3.7 Plus has 32.