Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 Omni 30B A3B Instruct
Alibaba
- DeepSeek-Coder-V2
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 Omni 30B A3B Instruct Alibaba | DeepSeek-Coder-V2 DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6 | 6 | |
| Math | 52.3 | — | |
| Speed | 96.2 t/s | — | |
| TTFT | 1.87 s | — | |
| Input · $ / 1M tokens | $0.25 | — | |
| Output · $ / 1M tokens | $0.97 | — | |
| Context window | 66K | Best: 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3 Omni 30B A3B Instruct
- 6
- DeepSeek-Coder-V2
- 6
Math
- Qwen3 Omni 30B A3B Instruct
- 52.3
- DeepSeek-Coder-V2
- —
Speed
- Qwen3 Omni 30B A3B Instruct
- 96.2 t/s
- DeepSeek-Coder-V2
- —
TTFT
- Qwen3 Omni 30B A3B Instruct
- 1.87 s
- DeepSeek-Coder-V2
- —
Input · $ / 1M tokens
- Qwen3 Omni 30B A3B Instruct
- $0.25
- DeepSeek-Coder-V2
- —
Output · $ / 1M tokens
- Qwen3 Omni 30B A3B Instruct
- $0.97
- DeepSeek-Coder-V2
- —
Context window
- Qwen3 Omni 30B A3B Instruct
- 66K
- DeepSeek-Coder-V2
- Best: 128K
Reasoning
- Qwen3 Omni 30B A3B Instruct
- No
- DeepSeek-Coder-V2
- No
Open weights
- Qwen3 Omni 30B A3B Instruct
- Yes
- DeepSeek-Coder-V2
- Yes
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 Omni 30B A3B Instruct6 · $0.43
Not plotted for lack of data on these axes: DeepSeek-Coder-V2.