Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 Next 80B A3B Instruct
Alibaba
- DeepSeek V3 0324
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 Next 80B A3B Instruct Alibaba | DeepSeek V3 0324 DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9.6 | Best: 9.7 | |
| Coding | — | 21.2 | |
| Math | Best: 66.3 | 41 | |
| Agentic | — | 0.8 | |
| Speed | Best: 150 t/s | 88.5 t/s | |
| TTFT | 0.86 s | Best: 0.72 s | |
| Input · $ / 1M tokens | Best: $0.15 | $0.24×1.6 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | $1.10×1.2 relative to the lowest price among the compared models | Best: $0.90 | |
| Context window | Best: 262K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0211 |
Intelligence
- Qwen3 Next 80B A3B Instruct
- 9.6
- DeepSeek V3 0324
- Best: 9.7
Coding
- Qwen3 Next 80B A3B Instruct
- —
- DeepSeek V3 0324
- 21.2
Math
- Qwen3 Next 80B A3B Instruct
- Best: 66.3
- DeepSeek V3 0324
- 41
Agentic
- Qwen3 Next 80B A3B Instruct
- —
- DeepSeek V3 0324
- 0.8
Speed
- Qwen3 Next 80B A3B Instruct
- Best: 150 t/s
- DeepSeek V3 0324
- 88.5 t/s
TTFT
- Qwen3 Next 80B A3B Instruct
- 0.86 s
- DeepSeek V3 0324
- Best: 0.72 s
Input · $ / 1M tokens
- Qwen3 Next 80B A3B Instruct
- Best: $0.15
- DeepSeek V3 0324
- $0.24×1.6 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Qwen3 Next 80B A3B Instruct
- $1.10×1.2 relative to the lowest price among the compared models
- DeepSeek V3 0324
- Best: $0.90
Context window
- Qwen3 Next 80B A3B Instruct
- Best: 262K
- DeepSeek V3 0324
- 128K
Reasoning
- Qwen3 Next 80B A3B Instruct
- No
- DeepSeek V3 0324
- No
Open weights
- Qwen3 Next 80B A3B Instruct
- Yes
- DeepSeek V3 0324
- Yes
Cost / task
- Qwen3 Next 80B A3B Instruct
- —
- DeepSeek V3 0324
- $0.0211
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 Next 80B A3B Instruct9.6 · $0.388
- DeepSeek V3 03249.7 · $0.405