Model comparison
o3-pro vs Qwen2.5-Max
o3-pro is the stronger model overall, scoring 42.9 to 40.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. o3-pro scores higher in 3 categories and Qwen2.5-Max in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 41.4.
- The biggest single-benchmark swing is Short-Story Creative Writing: 84.4% for o3-pro and 72.9% for Qwen2.5-Max.
Side by side
| o3-pro | Qwen2.5-Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 40.7 |
| Released | 2025-06-10 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $20 | — |
| Output $ / M tokens | $80 | — |
| Results tracked | 12 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Qwen2.5-Max: 41.8 (#117)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| WeirdML | 58.2% | — |
| LiveBench Coding | — | 64.4% |
| LMArena Coding | — | 1359 |
Reasoning Qwen2.5-Max leads
o3-pro: 23.8 (#171), Qwen2.5-Max: 25.6 (#147)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| Epoch Capabilities Index | 147.42 | 132.53 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| LiveBench Reasoning | — | 51.4% |
| LMArena Hard Prompts | — | 1360 |
| DTBench | 86.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 38.5% | — |
| LiveBench | — | 62.3% |
Math Not comparable
o3-pro: —, Qwen2.5-Max: 36.9 (#162)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | — | 58.4% |
| LMArena Math | — | 1369 |
Knowledge Qwen2.5-Max leads
o3-pro: 29.5 (#238), Qwen2.5-Max: 35.3 (#186)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| Confabulations | 14.2% | 21.8% |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1337 |
Multilingual Not comparable
o3-pro: —, Qwen2.5-Max: 48.1 (#146)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | — | 1352 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |
| LMArena Russian | — | 1353 |
| LMArena Spanish | — | 1377 |
Instruction Following Not comparable
o3-pro: —, Qwen2.5-Max: 71.3 (#152)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | — | 75.3% |
| LMArena Instruction Following | — | 1335 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Qwen2.5-Max: 41.4 (#142)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1358 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), Qwen2.5-Max: 55.4 (#146)
| Benchmark | o3-pro | Qwen2.5-Max |
|---|---|---|
| Short-Story Creative Writing | 84.4% | 72.9% |
| LMArena Text | — | 1367 |
| LMArena Creative Writing | — | 1339 |
| LMArena Multi-Turn | — | 1364 |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is o3-pro better than Qwen2.5-Max?
o3-pro is the stronger model overall, scoring 42.9 to 40.7 on the Noometry Index.
Is o3-pro or Qwen2.5-Max better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.
How many benchmarks do o3-pro and Qwen2.5-Max share?
3 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Qwen2.5-Max has 27.