Model comparison
Qwen2.5-Max vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 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 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 35.3.
Side by side
| Qwen2.5-Max | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 43.7 |
| Released | 2025-01-25 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $6 |
| Results tracked | 27 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Qwen2.5-Max: 41.8 (#117), Qwen3 Max: 43.0 (#93)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1359 | 1456 |
| LiveBench Coding | 64.4% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Qwen2.5-Max: —, Qwen3 Max: —
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen2.5-Max leads
Qwen2.5-Max: 25.6 (#147), Qwen3 Max: 22.6 (#190)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1448 |
| Epoch Capabilities Index | 132.53 | 142.38 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 51.4% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LiveBench Data Analysis | 67.9% | — |
| LMCA | — | 28.3% |
| LiveBench | 62.3% | — |
Math Qwen3 Max leads
Qwen2.5-Max: 36.9 (#162), Qwen3 Max: 38.7 (#131)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Math | 1369 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | 58.4% | — |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
Qwen2.5-Max: 35.3 (#186), Qwen3 Max: 48.1 (#78)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1337 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| Confabulations | 21.8% | — |
Multilingual Qwen3 Max leads
Qwen2.5-Max: 48.1 (#146), Qwen3 Max: 53.7 (#62)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1352 | 1429 |
| LMArena Chinese | 1382 | 1478 |
| LMArena French | 1396 | 1449 |
| LMArena German | 1350 | 1463 |
| LMArena Japanese | 1300 | 1397 |
| LMArena Korean | 1304 | 1399 |
| LMArena Russian | 1353 | 1428 |
| LMArena Spanish | 1377 | 1462 |
Instruction Following Qwen3 Max leads
Qwen2.5-Max: 71.3 (#152), Qwen3 Max: 74.8 (#87)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1335 | 1419 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Too close to call
Qwen2.5-Max: 41.4 (#142), Qwen3 Max: 41.6 (#134)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1358 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Qwen2.5-Max: 55.4 (#146), Qwen3 Max: 62.4 (#76)
| Benchmark | Qwen2.5-Max | Qwen3 Max |
|---|---|---|
| LMArena Text | 1367 | 1439 |
| LMArena Creative Writing | 1339 | 1402 |
| LMArena Multi-Turn | 1364 | 1446 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 40.7 on the Noometry Index.
Is Qwen2.5-Max or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 41.8 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Qwen3 Max share?
18 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3 Max has 33.