Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4.1 Flash (Max)
DeepSeek
- Qwen3.8 2.4T A95B
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4.1 Flash (Max) DeepSeek | Qwen3.8 2.4T A95B Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 39.5 | Best: 39.9 | |
| Coding | — | 71.9 | |
| Agentic | — | 50.1 | |
| Cyber Index | Best: 40.8% | 12.6% | |
| Speed | Best: 178 t/s | 41.2 t/s | |
| TTFT | Best: 0.98 s | 3 s | |
| Input · $ / 1M tokens | Best: $0.295 | $2×6.8 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 | 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | Best: $0.48 | $2.16×4.5 relative to the lowest price among the compared models |
Intelligence
- DeepSeek V4.1 Flash (Max)
- 39.5
- Qwen3.8 2.4T A95B
- Best: 39.9
Coding
- DeepSeek V4.1 Flash (Max)
- —
- Qwen3.8 2.4T A95B
- 71.9
Agentic
- DeepSeek V4.1 Flash (Max)
- —
- Qwen3.8 2.4T A95B
- 50.1
Cyber Index
- DeepSeek V4.1 Flash (Max)
- Best: 40.8%
- Qwen3.8 2.4T A95B
- 12.6%
Speed
- DeepSeek V4.1 Flash (Max)
- Best: 178 t/s
- Qwen3.8 2.4T A95B
- 41.2 t/s
TTFT
- DeepSeek V4.1 Flash (Max)
- Best: 0.98 s
- Qwen3.8 2.4T A95B
- 3 s
Input · $ / 1M tokens
- DeepSeek V4.1 Flash (Max)
- Best: $0.295
- Qwen3.8 2.4T A95B
- $2×6.8 relative to the lowest price among the compared models
Output · $ / 1M tokens
- DeepSeek V4.1 Flash (Max)
- Best: $1.20
- Qwen3.8 2.4T A95B
- $6×5 relative to the lowest price among the compared models
Context window
- DeepSeek V4.1 Flash (Max)
- Best: 1M
- Qwen3.8 2.4T A95B
- 262K
Reasoning
- DeepSeek V4.1 Flash (Max)
- Yes
- Qwen3.8 2.4T A95B
- Yes
Open weights
- DeepSeek V4.1 Flash (Max)
- Yes
- Qwen3.8 2.4T A95B
- Yes
Cost / task
- DeepSeek V4.1 Flash (Max)
- Best: $0.48
- Qwen3.8 2.4T A95B
- $2.16×4.5 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 (Max)39.5 · $0.48
- Qwen3.8 2.4T A95B39.9 · $2.16