Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.1 (Non-reasoning)
OpenAI
- Qwen3.5 9B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.1 (Non-reasoning) OpenAI | Qwen3.5 9B (Reasoning) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 13.3 | 13.3 | |
| Coding | — | 28.7 | |
| Math | 38 | — | |
| Agentic | — | 1.2 | |
| Speed | Best: 114 t/s | 64.2 t/s | |
| TTFT | Best: 1.12 s | 1.59 s | |
| Input · $ / 1M tokens | $1.25×9.3 relative to the lowest price among the compared models | Best: $0.135 | |
| Output · $ / 1M tokens | $10×50 relative to the lowest price among the compared models | Best: $0.20 | |
| Context window | 1M | 1M | |
| Reasoning | No | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.213 |
Intelligence
- GPT-5.1 (Non-reasoning)
- 13.3
- Qwen3.5 9B (Reasoning)
- 13.3
Coding
- GPT-5.1 (Non-reasoning)
- —
- Qwen3.5 9B (Reasoning)
- 28.7
Math
- GPT-5.1 (Non-reasoning)
- 38
- Qwen3.5 9B (Reasoning)
- —
Agentic
- GPT-5.1 (Non-reasoning)
- —
- Qwen3.5 9B (Reasoning)
- 1.2
Speed
- GPT-5.1 (Non-reasoning)
- Best: 114 t/s
- Qwen3.5 9B (Reasoning)
- 64.2 t/s
TTFT
- GPT-5.1 (Non-reasoning)
- Best: 1.12 s
- Qwen3.5 9B (Reasoning)
- 1.59 s
Input · $ / 1M tokens
- GPT-5.1 (Non-reasoning)
- $1.25×9.3 relative to the lowest price among the compared models
- Qwen3.5 9B (Reasoning)
- Best: $0.135
Output · $ / 1M tokens
- GPT-5.1 (Non-reasoning)
- $10×50 relative to the lowest price among the compared models
- Qwen3.5 9B (Reasoning)
- Best: $0.20
Context window
- GPT-5.1 (Non-reasoning)
- 1M
- Qwen3.5 9B (Reasoning)
- 1M
Reasoning
- GPT-5.1 (Non-reasoning)
- No
- Qwen3.5 9B (Reasoning)
- Yes
Open weights
- GPT-5.1 (Non-reasoning)
- No
- Qwen3.5 9B (Reasoning)
- Yes
Cost / task
- GPT-5.1 (Non-reasoning)
- —
- Qwen3.5 9B (Reasoning)
- $0.213
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- GPT-5.1 (Non-reasoning)13.3 · $3.44
- Qwen3.5 9B (Reasoning)13.3 · $0.151