Model comparison
o3 vs Qwen1.5 4b Chat
o3 is the stronger model overall, scoring 47.5 to 28.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. o3 scores higher in 8 categories and Qwen1.5 4b Chat in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o3 leads 63.5 to 23.8.
- Qwen1.5 4b Chat has downloadable open weights; the other is API-only.
Side by side
| o3 | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 28.8 |
| Released | 2025-04-16 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 63 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1408 | 999 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Qwen1.5 4b Chat: —
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| 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), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1402 | 976 |
| 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% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.86 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1426 | 1026 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1402 | 980 |
| 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% | — |
Multimodal Not comparable
o3: 41.4 (#36), Qwen1.5 4b Chat: —
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1401 | 979 |
| LMArena Chinese | 1437 | 1024 |
| LMArena German | 1420 | 902 |
| LMArena Russian | 1406 | 952 |
| LMArena French | 1430 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
| LMArena Spanish | 1395 | — |
Instruction Following o3 leads
o3: 72.8 (#127), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1368 | 978 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1372 | 988 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | o3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1410 | 997 |
| LMArena Creative Writing | 1359 | 969 |
| LMArena Multi-Turn | 1405 | 977 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Qwen1.5 4b Chat?
o3 is the stronger model overall, scoring 47.5 to 28.8 on the Noometry Index.
Is o3 or Qwen1.5 4b Chat better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 29.1 in the Noometry coding category.
How many benchmarks do o3 and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen1.5 4b Chat has 13.