Model comparison
o3 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 47.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. o3 scores higher in 1 category and Qwen3.6 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 41.7 to 32.0.
- The biggest single-benchmark swing is Chess Puzzles: 38% for o3 and 20% for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview is cheaper at $1.30 / $7.80 per million input/output tokens, against $2 / $8 for o3.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 200K.
Side by side
| o3 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 51.5 |
| Released | 2025-04-16 | 2026-04-20 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 262K |
| Max output | 100K | 66K |
| Input $ / M tokens | $2 | $1.30 |
| Output $ / M tokens | $8 | $7.80 |
| Results tracked | 63 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
o3: 46.8 (#64), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| SWE-bench Verified | 62.3% | 76.7% |
| LMArena Coding | 1408 | 1471 |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| LMArena WebDev | — | 1482 |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Qwen3.6 Max Preview: —
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
o3: 32.0 (#78), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 53.1% | 63% |
| Chess Puzzles | 38% | 20% |
| LMArena Hard Prompts | 1402 | 1457 |
| Mystery Game Puzzles | 29% | 19% |
| DTBench | 84.8% | 87.2% |
| LMCA | 39.7% | 42.5% |
| Epoch Capabilities Index | 146.86 | 149.24 |
| ARC-AGI-2 | 6.5% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| EnigmaEval | 13.1% | — |
| ForecastBench | 62.5 | — |
Math Qwen3.6 Max Preview leads
o3: 50.2 (#58), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.4% | 91.1% |
| LMArena Math | 1426 | 1465 |
| FrontierMath (Feb 2025 set) | 18.7% | 23.1% |
| FrontierMath Tier 4 (v1) | 2.1% | 4.2% |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
Knowledge Qwen3.6 Max Preview leads
o3: 54.6 (#52), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 81.8% | 87.4% |
| SimpleQA Verified | 49.4% | 52% |
| LMArena Expert | 1402 | 1478 |
| Humanity's Last Exam | 20.3% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
Multimodal Not comparable
o3: 41.4 (#36), Qwen3.6 Max Preview: —
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual Qwen3.6 Max Preview leads
o3: 51.7 (#105), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1401 | 1437 |
| LMArena Chinese | 1437 | 1487 |
| LMArena French | 1430 | 1449 |
| LMArena Russian | 1406 | 1445 |
| LMArena Spanish | 1395 | 1454 |
| LMArena German | 1420 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
Instruction Following Qwen3.6 Max Preview leads
o3: 72.8 (#127), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1368 | 1438 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1372 | 1457 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference Too close to call
o3: 63.5 (#64), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | o3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1410 | 1447 |
| LMArena Creative Writing | 1359 | 1435 |
| LMArena Multi-Turn | 1405 | 1456 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 47.5 on the Noometry Index.
Which is cheaper, o3 or Qwen3.6 Max Preview?
Qwen3.6 Max Preview is cheaper. It lists at $1.30 per million input tokens and $7.80 per million output tokens; o3 lists at $2 and $8.
Is o3 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 200K.
How many benchmarks do o3 and Qwen3.6 Max Preview share?
26 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Qwen3.6 Max Preview has 29.