Model comparison
Qwen2.5-Max vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 40.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen2.5-Max scores higher in 1 category and Qwen3.5 27B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 27B leads 59.3 to 55.4.
- Qwen3.5 27B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Max | Qwen3.5 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 41.9 |
| Released | 2025-01-25 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 27 | 28 |
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), Qwen3.5 27B: 38.9 (#168)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Coding | 1359 | 1427 |
| LMArena WebDev | — | 1358 |
| WeirdML | — | 39.5% |
| LiveBench Coding | 64.4% | — |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Qwen2.5-Max: —, Qwen3.5 27B: —
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Qwen2.5-Max: 25.6 (#147), Qwen3.5 27B: 27.5 (#117)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1414 |
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| LiveBench Reasoning | 51.4% | — |
| DTBench | — | 82.4% |
| LiveBench Data Analysis | 67.9% | — |
| LMCA | — | 34% |
| Epoch Capabilities Index | 132.53 | — |
| LiveBench | 62.3% | — |
Math Qwen3.5 27B leads
Qwen2.5-Max: 36.9 (#162), Qwen3.5 27B: 38.8 (#127)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1369 | 1429 |
| MathArena Final-Answer Competitions | — | 56.7% |
| LiveBench Math | 58.4% | — |
Knowledge Qwen3.5 27B leads
Qwen2.5-Max: 35.3 (#186), Qwen3.5 27B: 38.0 (#150)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1337 | 1428 |
| Confabulations | 21.8% | — |
| Vectara Hallucination Rate | — | 12.1% |
Multimodal Not comparable
Qwen2.5-Max: —, Qwen3.5 27B: 39.4 (#59)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1241 |
Multilingual Qwen3.5 27B leads
Qwen2.5-Max: 48.1 (#146), Qwen3.5 27B: 50.8 (#115)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1352 | 1390 |
| LMArena Chinese | 1382 | 1478 |
| LMArena French | 1396 | 1410 |
| LMArena German | 1350 | 1393 |
| LMArena Japanese | 1300 | 1345 |
| LMArena Korean | 1304 | 1358 |
| LMArena Russian | 1353 | 1390 |
| LMArena Spanish | 1377 | 1407 |
Instruction Following Qwen3.5 27B leads
Qwen2.5-Max: 71.3 (#152), Qwen3.5 27B: 73.5 (#119)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1393 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Qwen3.5 27B leads
Qwen2.5-Max: 41.4 (#142), Qwen3.5 27B: 43.1 (#106)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1358 | 1413 |
Writing & Preference Qwen3.5 27B leads
Qwen2.5-Max: 55.4 (#146), Qwen3.5 27B: 59.3 (#111)
| Benchmark | Qwen2.5-Max | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1367 | 1409 |
| LMArena Creative Writing | 1339 | 1362 |
| LMArena Multi-Turn | 1364 | 1410 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 40.7 on the Noometry Index.
Is Qwen2.5-Max or Qwen3.5 27B better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 38.9 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Qwen3.5 27B share?
17 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3.5 27B has 28.