Model comparison
o3-pro vs Qwen-14B
o3-pro is the stronger model overall, scoring 42.9 to 31.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. o3-pro scores higher in 4 categories and Qwen-14B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 31.3.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 31.4 |
| Released | 2025-06-10 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $20 | — |
| Output $ / M tokens | $80 | — |
| Results tracked | 12 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Qwen-14B: 31.2 (#288)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1071 |
Reasoning o3-pro leads
o3-pro: 23.8 (#171), Qwen-14B: 19.6 (#257)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 147.42 | 113.03 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| LMArena Hard Prompts | — | 1027 |
| DTBench | 86.9% | — |
| LMCA | 38.5% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Not comparable
o3-pro: —, Qwen-14B: 31.2 (#227)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
o3-pro: 29.5 (#238), Qwen-14B: —
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Not comparable
o3-pro: —, Qwen-14B: 27.5 (#275)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
o3-pro: —, Qwen-14B: 52.4 (#289)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Qwen-14B: 31.3 (#280)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1028 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), Qwen-14B: 27.6 (#299)
| Benchmark | o3-pro | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| Short-Story Creative Writing | 84.4% | — |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is o3-pro better than Qwen-14B?
o3-pro is the stronger model overall, scoring 42.9 to 31.4 on the Noometry Index.
Is o3-pro or Qwen-14B better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 31.2 in the Noometry coding category.
How many benchmarks do o3-pro and Qwen-14B share?
1 benchmark has published results for both models. o3-pro has 12 scored results on Noometry and Qwen-14B has 18.