Model comparison
o3 vs Qwen2.5-Coder-32B
o3 is the stronger model overall, scoring 47.5 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 4.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. o3 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3 leads 46.8 to 22.6.
- The biggest single-benchmark swing is Aider Polyglot: 81.3% for o3 and 16.4% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| o3 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 33.4 |
| Released | 2025-04-16 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | 200K | 33K |
| Max output | 100K | 29K |
| Input $ / M tokens | $2 | $0.66 |
| Output $ / M tokens | $8 | $1 |
| Results tracked | 63 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 58.4% | 9% |
| Aider Polyglot | 81.3% | 16.4% |
| LMArena Coding | 1408 | 1276 |
| SWE-bench Verified | 62.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Qwen2.5-Coder-32B: —
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1251 |
| Epoch Capabilities Index | 146.86 | 119.49 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 39.7% | — |
| ForecastBench | 62.5 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math o3 leads
o3: 50.2 (#58), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1426 | 1251 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 93% |
Knowledge o3 leads
o3: 54.6 (#52), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1402 | 1221 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
o3: 41.4 (#36), Qwen2.5-Coder-32B: —
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1401 | 1205 |
| LMArena Chinese | 1437 | 1222 |
| LMArena Russian | 1406 | 1228 |
| LMArena French | 1430 | — |
| LMArena German | 1420 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
| LMArena Spanish | 1395 | — |
Instruction Following o3 leads
o3: 72.8 (#127), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1368 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1372 | 1251 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | o3 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1410 | 1230 |
| LMArena Creative Writing | 1359 | 1174 |
| LMArena Multi-Turn | 1405 | 1222 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is o3 better than Qwen2.5-Coder-32B?
o3 is the stronger model overall, scoring 47.5 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 4.7× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 or Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; o3 lists at $2 and $8.
Is o3 or Qwen2.5-Coder-32B better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 33K.
How many benchmarks do o3 and Qwen2.5-Coder-32B share?
15 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen2.5-Coder-32B has 31.