Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4.1 Flash 1017 (Max)
DeepSeek
- Qwen3.8 Max (0902)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4.1 Flash 1017 (Max) DeepSeek | Qwen3.8 Max (0902) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 45.1 | Best: 45.4 | |
| Coding | — | 76.2 | |
| Agentic | — | 56 | |
| Speed | Best: 225 t/s | 38.2 t/s | |
| TTFT | Best: 1.12 s | 3.06 s | |
| Input · $ / 1M tokens | Best: $0.30 | $2×6.7 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $1.20 | $6×5 relative to the lowest price among the compared models | |
| Context window | Best: 1M | 984K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | Best: $0.262 | $5.41×20.6 relative to the lowest price among the compared models |
Intelligence
- DeepSeek V4.1 Flash 1017 (Max)
- 45.1
- Qwen3.8 Max (0902)
- Best: 45.4
Coding
- DeepSeek V4.1 Flash 1017 (Max)
- —
- Qwen3.8 Max (0902)
- 76.2
Agentic
- DeepSeek V4.1 Flash 1017 (Max)
- —
- Qwen3.8 Max (0902)
- 56
Speed
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 225 t/s
- Qwen3.8 Max (0902)
- 38.2 t/s
TTFT
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 1.12 s
- Qwen3.8 Max (0902)
- 3.06 s
Input · $ / 1M tokens
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $0.30
- Qwen3.8 Max (0902)
- $2×6.7 relative to the lowest price among the compared models
Output · $ / 1M tokens
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $1.20
- Qwen3.8 Max (0902)
- $6×5 relative to the lowest price among the compared models
Context window
- DeepSeek V4.1 Flash 1017 (Max)
- Best: 1M
- Qwen3.8 Max (0902)
- 984K
Reasoning
- DeepSeek V4.1 Flash 1017 (Max)
- Yes
- Qwen3.8 Max (0902)
- Yes
Open weights
- DeepSeek V4.1 Flash 1017 (Max)
- Yes
- Qwen3.8 Max (0902)
- No
Cost / task
- DeepSeek V4.1 Flash 1017 (Max)
- Best: $0.262
- Qwen3.8 Max (0902)
- $5.41×20.6 relative to the lowest price among the compared models
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.
- DeepSeek V4.1 Flash 1017 (Max)45.1 · $0.262
- Qwen3.8 Max (0902)45.4 · $5.41