Model comparison
o3-pro vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 42.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. o3-pro scores higher in 2 categories and Qwen3.5 397B-A17B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 44.1.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $20 / $80 for o3-pro.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 200K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.9 | 46.0 |
| Released | 2025-06-10 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 66K |
| Input $ / M tokens | $20 | $0.60 |
| Output $ / M tokens | $80 | $3.60 |
| Results tracked | 12 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| LMArena WebDev | — | 1400 |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1465 |
Agentic & Tool Use Not comparable
o3-pro: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
o3-pro: 23.8 (#171), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 72.1% | 73.7% |
| DTBench | 86.9% | 87.5% |
| LMCA | 38.5% | 37.9% |
| Epoch Capabilities Index | 147.42 | 146.65 |
| ARC-AGI-2 | 4.9% | — |
| NYT Connections (extended) | — | 58.9% |
| ARC-AGI-1 | 59.3% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 18% |
Math Not comparable
o3-pro: —, Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1454 |
Knowledge Qwen3.5 397B-A17B leads
o3-pro: 29.5 (#238), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | — | 86.4% |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1462 |
Multimodal Not comparable
o3-pro: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Not comparable
o3-pro: —, Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |
Instruction Following Not comparable
o3-pro: —, Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | — | 1424 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
o3-pro: 57.1 (#133), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | — | 1438 |
| LMArena Creative Writing | — | 1401 |
| Short-Story Creative Writing | 84.4% | — |
| EQ-Bench Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is o3-pro better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 42.9 on the Noometry Index.
Which is cheaper, o3-pro or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; o3-pro lists at $20 and $80.
Is o3-pro or Qwen3.5 397B-A17B better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 200K.
How many benchmarks do o3-pro and Qwen3.5 397B-A17B share?
4 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Qwen3.5 397B-A17B has 36.