Model comparison
Qwen2.5-Max vs Qwen2-72B
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.0 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 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Max leads 55.4 to 40.8.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Max | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 30.0 |
| Released | 2025-01-25 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1359 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 64.4% | — |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Qwen2.5-Max: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2.5-Max leads
Qwen2.5-Max: 25.6 (#147), Qwen2-72B: 23.2 (#181)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1191 |
| Epoch Capabilities Index | 132.53 | 125.28 |
| LiveBench Reasoning | 51.4% | — |
| LiveBench Data Analysis | 67.9% | — |
| LiveBench | 62.3% | — |
Math Qwen2.5-Max leads
Qwen2.5-Max: 36.9 (#162), Qwen2-72B: 30.2 (#236)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Math | 1369 | 1235 |
| LiveBench Math | 58.4% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Qwen2.5-Max leads
Qwen2.5-Max: 35.3 (#186), Qwen2-72B: 21.2 (#275)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1337 | 1171 |
| GPQA Diamond | — | 40.8% |
| Confabulations | 21.8% | — |
| MMLU | — | 82.4% |
Multilingual Qwen2.5-Max leads
Qwen2.5-Max: 48.1 (#146), Qwen2-72B: 35.9 (#244)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1352 | 1176 |
| LMArena Chinese | 1382 | 1240 |
| LMArena French | 1396 | 1170 |
| LMArena German | 1350 | 1151 |
| LMArena Japanese | 1300 | 1111 |
| LMArena Korean | 1304 | 1083 |
| LMArena Russian | 1353 | 1169 |
| LMArena Spanish | 1377 | 1169 |
Instruction Following Qwen2.5-Max leads
Qwen2.5-Max: 71.3 (#152), Qwen2-72B: 61.7 (#241)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1181 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Qwen2.5-Max leads
Qwen2.5-Max: 41.4 (#142), Qwen2-72B: 36.1 (#235)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1358 | 1192 |
Writing & Preference Qwen2.5-Max leads
Qwen2.5-Max: 55.4 (#146), Qwen2-72B: 40.8 (#241)
| Benchmark | Qwen2.5-Max | Qwen2-72B |
|---|---|---|
| LMArena Text | 1367 | 1203 |
| LMArena Creative Writing | 1339 | 1181 |
| LMArena Multi-Turn | 1364 | 1196 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Qwen2-72B?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.0 on the Noometry Index.
Is Qwen2.5-Max or Qwen2-72B better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Qwen2-72B share?
18 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen2-72B has 26.