Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3.8 2.4T A95B
Alibaba
- DeepSeek V4.1 Flash (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3.8 2.4T A95B Alibaba | DeepSeek V4.1 Flash (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 39.9 | 39.5 | |
| Coding | 71.9 | — | |
| Agentic | 50.1 | — | |
| Cyber Index | 12.6% | Best: 40.8% | |
| Speed | 39.5 t/s | Best: 174 t/s | |
| TTFT | 2.96 s | Best: 1.15 s | |
| Input · $ / 1M tokens | $2×6.7 relative to the lowest price among the compared models | Best: $0.30 | |
| Output · $ / 1M tokens | $6×5 relative to the lowest price among the compared models | Best: $1.20 | |
| Context window | 262K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | $2.16×8.1 relative to the lowest price among the compared models | Best: $0.265 |
Intelligence
- Qwen3.8 2.4T A95B
- Best: 39.9
- DeepSeek V4.1 Flash (Max)
- 39.5
Coding
- Qwen3.8 2.4T A95B
- 71.9
- DeepSeek V4.1 Flash (Max)
- —
Agentic
- Qwen3.8 2.4T A95B
- 50.1
- DeepSeek V4.1 Flash (Max)
- —
Cyber Index
- Qwen3.8 2.4T A95B
- 12.6%
- DeepSeek V4.1 Flash (Max)
- Best: 40.8%
Speed
- Qwen3.8 2.4T A95B
- 39.5 t/s
- DeepSeek V4.1 Flash (Max)
- Best: 174 t/s
TTFT
- Qwen3.8 2.4T A95B
- 2.96 s
- DeepSeek V4.1 Flash (Max)
- Best: 1.15 s
Input · $ / 1M tokens
- Qwen3.8 2.4T A95B
- $2×6.7 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash (Max)
- Best: $0.30
Output · $ / 1M tokens
- Qwen3.8 2.4T A95B
- $6×5 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash (Max)
- Best: $1.20
Context window
- Qwen3.8 2.4T A95B
- 262K
- DeepSeek V4.1 Flash (Max)
- Best: 1M
Reasoning
- Qwen3.8 2.4T A95B
- Yes
- DeepSeek V4.1 Flash (Max)
- Yes
Open weights
- Qwen3.8 2.4T A95B
- Yes
- DeepSeek V4.1 Flash (Max)
- No
Cost / task
- Qwen3.8 2.4T A95B
- $2.16×8.1 relative to the lowest price among the compared models
- DeepSeek V4.1 Flash (Max)
- Best: $0.265
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.
- Qwen3.8 2.4T A95B39.9 · $2.16
- DeepSeek V4.1 Flash (Max)39.5 · $0.265