Model comparison
o3 vs Qwen3 8B
o3 is the stronger model overall, scoring 47.5 to 33.7 on the Noometry Index. Qwen3 8B costs 11× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. o3 scores higher in 6 categories and Qwen3 8B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 36.1.
- The biggest single-benchmark swing is Chess Puzzles: 38% for o3 and 5% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 131K.
- Qwen3 8B has downloadable open weights; the other is API-only.
Side by side
| o3 | Qwen3 8B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 33.7 |
| Released | 2025-04-16 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 100K | 8K |
| Input $ / M tokens | $2 | $0.18 |
| Output $ / M tokens | $8 | $0.70 |
| Results tracked | 63 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Qwen3 8B: 34.0 (#248)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| SciCode | — | 22.6% |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| LMArena Coding | 1408 | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use o3 leads
o3: 34.5 (#44), Qwen3 8B: 30.2 (#78)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | 42.6% |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Qwen3 8B: 16.6 (#303)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| CritPt | 1.4% | 0% |
| Chess Puzzles | 38% | 5% |
| DTBench | 84.8% | 59.7% |
| LMCA | 39.7% | 8.8% |
| Epoch Capabilities Index | 146.86 | 136.17 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| EnigmaEval | 13.1% | — |
| LMArena Hard Prompts | 1402 | — |
| Mystery Game Puzzles | 29% | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Qwen3 8B: 34.9 (#191)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.4% | 56.1% |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| Omni-MATH | 71.4% | — |
| LMArena Math | 1426 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Qwen3 8B: 36.1 (#173)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 81.8% | 56.8% |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| Vectara Hallucination Rate | — | 4.8% |
| GPQA (HELM) | 75.3% | — |
| LMArena Expert | 1402 | — |
Multimodal Not comparable
o3: 41.4 (#36), Qwen3 8B: —
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual Not comparable
o3: 51.7 (#105), Qwen3 8B: —
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1401 | — |
| LMArena Chinese | 1437 | — |
| LMArena French | 1430 | — |
| LMArena German | 1420 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
| LMArena Russian | 1406 | — |
| LMArena Spanish | 1395 | — |
Instruction Following Not comparable
o3: 72.8 (#127), Qwen3 8B: —
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| IFEval | 86.9% | — |
| LMArena Instruction Following | 1368 | — |
Long Context o3 leads
o3: 53.3 (#6), Qwen3 8B: 37.9 (#210)
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | 88.9% | 62.1% |
| CL-bench | 17.8% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Not comparable
o3: 63.5 (#64), Qwen3 8B: —
| Benchmark | o3 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1410 | — |
| LMArena Creative Writing | 1359 | — |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
| LMArena Multi-Turn | 1405 | — |
Frequently asked questions
Is o3 better than Qwen3 8B?
o3 is the stronger model overall, scoring 47.5 to 33.7 on the Noometry Index. Qwen3 8B costs 11× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; o3 lists at $2 and $8.
Is o3 or Qwen3 8B better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 131K.
How many benchmarks do o3 and Qwen3 8B share?
9 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3 8B has 11.