Model comparison
o3-pro vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. o3-pro scores higher in 2 categories and Qwen3.6 Plus in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 45.2.
- The biggest single-benchmark swing is LMCA: 38.5% for o3-pro and 33.1% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $20 / $80 for o3-pro.
- Qwen3.6 Plus accepts more context: 1M tokens versus 200K.
Side by side
| o3-pro | Qwen3.6 Plus | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 47.5 |
| Released | 2025-06-10 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 100K | 66K |
| Input $ / M tokens | $20 | $0.50 |
| Output $ / M tokens | $80 | $3 |
| Results tracked | 12 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | — | 57.9% |
| Aider Polyglot | 84.9% | — |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1467 |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
o3-pro: —, Qwen3.6 Plus: —
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
o3-pro: 23.8 (#171), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| DTBench | 86.9% | 81.9% |
| LMCA | 38.5% | 33.1% |
| Epoch Capabilities Index | 147.42 | 147.65 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| NYT Connections (extended) | — | 60.3% |
| ARC-AGI-1 | 59.3% | — |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| LMArena Hard Prompts | — | 1449 |
| Mystery Game Puzzles | — | 12% |
Math Not comparable
o3-pro: —, Qwen3.6 Plus: 51.8 (#54)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| LMArena Math | — | 1450 |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
o3-pro: 29.5 (#238), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1454 |
Multilingual Not comparable
o3-pro: —, Qwen3.6 Plus: 53.3 (#70)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | — | 1424 |
| LMArena Chinese | — | 1477 |
| LMArena French | — | 1455 |
| LMArena German | — | 1452 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1379 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1432 |
Instruction Following Not comparable
o3-pro: —, Qwen3.6 Plus: 75.0 (#74)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | — | 1425 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| CL-bench | — | 20.3% |
| LMArena Longer Query | — | 1439 |
Writing & Preference Qwen3.6 Plus leads
o3-pro: 57.1 (#133), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | o3-pro | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | — | 1437 |
| LMArena Creative Writing | — | 1404 |
| Short-Story Creative Writing | 84.4% | — |
| LMArena Multi-Turn | — | 1438 |
Frequently asked questions
Is o3-pro better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.9 on the Noometry Index.
Which is cheaper, o3-pro or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; o3-pro lists at $20 and $80.
Is o3-pro or Qwen3.6 Plus better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 200K.
How many benchmarks do o3-pro and Qwen3.6 Plus share?
3 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Qwen3.6 Plus has 37.