Model comparison
Qwen Max vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 34.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen Max scores higher in 0 categories and Qwen2.5-Max in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 22.3.
Side by side
| Qwen Max | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.7 | 40.7 |
| Released | 2024-04-03 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 33K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.60 | — |
| Output $ / M tokens | $6.40 | — |
| Results tracked | 23 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Qwen Max: 30.7 (#292), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1288 | 1359 |
| Aider Polyglot | 21.8% | — |
| LiveBench Coding | — | 64.4% |
Reasoning Too close to call
Qwen Max: 25.1 (#151), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1360 |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.53 |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Qwen Max: 22.3 (#276), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1275 | 1369 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Qwen2.5-Max leads
Qwen Max: 30.3 (#228), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1248 | 1337 |
| GPQA Diamond | 56.1% | — |
| Confabulations | — | 21.8% |
Multilingual Qwen2.5-Max leads
Qwen Max: 41.8 (#202), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1263 | 1352 |
| LMArena Chinese | 1254 | 1382 |
| LMArena French | 1330 | 1396 |
| LMArena German | 1254 | 1350 |
| LMArena Japanese | 1205 | 1300 |
| LMArena Korean | 1142 | 1304 |
| LMArena Russian | 1274 | 1353 |
| LMArena Spanish | 1290 | 1377 |
Instruction Following Qwen2.5-Max leads
Qwen Max: 66.5 (#208), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1262 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Qwen Max: 39.4 (#180), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1288 | 1358 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Qwen2.5-Max leads
Qwen Max: 47.8 (#205), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Qwen Max | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1282 | 1367 |
| LMArena Creative Writing | 1248 | 1339 |
| LMArena Multi-Turn | 1277 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Qwen Max better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 34.7 on the Noometry Index.
Is Qwen Max or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 30.7 in the Noometry coding category.
How many benchmarks do Qwen Max and Qwen2.5-Max share?
17 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen2.5-Max has 27.