Model comparison
o3 vs Qwen3.6 27B
o3 is the stronger model overall, scoring 47.5 to 42.2 on the Noometry Index. Qwen3.6 27B costs 2.6× 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 5 categories and Qwen3.6 27B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o3 leads 63.5 to 50.3.
- The biggest single-benchmark swing is Mystery Game Puzzles: 29% for o3 and 7% for Qwen3.6 27B.
- Qwen3.6 27B is cheaper at $0.60 / $3.60 per million input/output tokens, against $2 / $8 for o3.
- Qwen3.6 27B accepts more context: 262K tokens versus 200K.
- Qwen3.6 27B has downloadable open weights; the other is API-only.
Side by side
| o3 | Qwen3.6 27B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 42.2 |
| Released | 2025-04-16 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 66K |
| Input $ / M tokens | $2 | $0.60 |
| Output $ / M tokens | $8 | $3.60 |
| 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), Qwen3.6 27B: 39.1 (#163)
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| SciCode | — | 37.3% |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| LMArena Coding | 1408 | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Qwen3.6 27B: —
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| 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), Qwen3.6 27B: 25.0 (#153)
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| CritPt | 1.4% | 0.9% |
| Chess Puzzles | 38% | 22% |
| Mystery Game Puzzles | 29% | 7% |
| DTBench | 84.8% | 78.1% |
| LMCA | 39.7% | 34.5% |
| Epoch Capabilities Index | 146.86 | 146.5 |
| 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 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Qwen3.6 27B: 48.5 (#62)
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 35.1% |
| OTIS Mock AIME 2024-2025 | 84.4% | 91.1% |
| 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), Qwen3.6 27B: 52.4 (#63)
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | 81.8% | 85.9% |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
| LMArena Expert | 1402 | — |
Multimodal Not comparable
o3: 41.4 (#36), Qwen3.6 27B: —
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual Not comparable
o3: 51.7 (#105), Qwen3.6 27B: —
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| 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), Qwen3.6 27B: —
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| IFEval | 86.9% | — |
| LMArena Instruction Following | 1368 | — |
Long Context Not comparable
o3: 53.3 (#6), Qwen3.6 27B: —
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Qwen3.6 27B: 50.3 (#181)
| Benchmark | o3 | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1410 | — |
| LMArena Creative Writing | 1359 | — |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1405 | — |
Frequently asked questions
Is o3 better than Qwen3.6 27B?
o3 is the stronger model overall, scoring 47.5 to 42.2 on the Noometry Index. Qwen3.6 27B costs 2.6× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 or Qwen3.6 27B?
Qwen3.6 27B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; o3 lists at $2 and $8.
Is o3 or Qwen3.6 27B better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 27B does, with 262K tokens against 200K.
How many benchmarks do o3 and Qwen3.6 27B share?
9 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3.6 27B has 11.