Model comparison
o3-pro vs Qwen2.5 72B Instruct
o3-pro is the stronger model overall, scoring 42.9 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 14× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. o3-pro scores higher in 5 categories and Qwen2.5 72B Instruct in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 38.9.
- The biggest single-benchmark swing is WeirdML: 58.2% for o3-pro and 16% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 31.9 |
| Released | 2025-06-10 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 100K | 8K |
| Input $ / M tokens | $20 | $1.40 |
| Output $ / M tokens | $80 | $5.60 |
| Results tracked | 12 | 43 |
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 72B Instruct: 33.2 (#260)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 58.2% | 16% |
| Aider Polyglot | 84.9% | — |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1292 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
o3-pro: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning o3-pro leads
o3-pro: 23.8 (#171), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| DTBench | 86.9% | 62.9% |
| LMCA | 38.5% | 13.4% |
| Epoch Capabilities Index | 147.42 | 129 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| LMArena Hard Prompts | — | 1271 |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Not comparable
o3-pro: —, Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge o3-pro leads
o3-pro: 29.5 (#238), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| Confabulations | 14.2% | 19.1% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Vectara Hallucination Rate | 23.3% | — |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
o3-pro: —, Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Not comparable
o3-pro: —, Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1282 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | o3-pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| Short-Story Creative Writing | 84.4% | — |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is o3-pro better than Qwen2.5 72B Instruct?
o3-pro is the stronger model overall, scoring 42.9 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 14× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, o3-pro or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; o3-pro lists at $20 and $80.
Is o3-pro or Qwen2.5 72B Instruct better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 131K.
How many benchmarks do o3-pro and Qwen2.5 72B Instruct share?
5 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Qwen2.5 72B Instruct has 43.