token.app › Compare › o1 vs Qwen3.6 35B A3B
o1 vs Qwen3.6 35B A3B
Qwen3.6 35B A3B leads on 3 of 3 shared benchmarks. Qwen3.6 35B A3B is 84× cheaper per token on a blended 3:1 basis. Qwen3.6 35B A3B accepts the larger context window (262K).
Head to head
Blended price uses a 3:1 input:output mix
| o1 | Qwen3.6 35B A3B | |
|---|---|---|
| Provider | OpenAI | Alibaba |
| Input $/1M | $15.00 | $0.100 |
| Output $/1M | $60.00 | $0.950 |
| Blended $/1M | $26.25 | $0.313 |
| Context window | 200K | 262K |
| Max output | 100K | 236K |
| Released | Dec 2024 | Apr 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 76.8% | 84.8% |
| FrontierMath T1–3 | 14.7% | 20.4% |
| OTIS Mock AIME | 73.3% | 86.7% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose o1 if…
- No clear advantage on the data we hold.
Choose Qwen3.6 35B A3B if…
- Costs less per token — $0.313 vs $26.25 blended
- Higher GPQA Diamond (84.8% vs 76.8%)
- Higher FrontierMath T1–3 (20.4% vs 14.7%)
- Higher OTIS Mock AIME (86.7% vs 73.3%)
- Larger context window (262K)
- Open weights — self-hostable
- Newer model (released Apr 2026)
FAQ
Which is better, o1 or Qwen3.6 35B A3B?
Across the 3 benchmarks both models have independently-run scores for, o1 leads on 0 and Qwen3.6 35B A3B leads on 3. Benchmarks are one input — price and context window are on this page too.
Is o1 cheaper than Qwen3.6 35B A3B?
Qwen3.6 35B A3B is cheaper: $0.313 versus $26.25 per million tokens blended at 3:1 input:output. Input alone: $15.00 vs $0.100. Output alone: $60.00 vs $0.950.
What context windows do o1 and Qwen3.6 35B A3B have?
o1: 200,000 tokens. Qwen3.6 35B A3B: 262,144 tokens.
Who makes o1 and Qwen3.6 35B A3B?
o1 is made by OpenAI. Qwen3.6 35B A3B is made by Alibaba.