Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 30B A3B 2507 Instruct
Alibaba
- Devstral Small 2
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 30B A3B 2507 Instruct Alibaba | Devstral Small 2 Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.5 | 7.5 | |
| Coding | — | 29.3 | |
| Math | Best: 66.3 | 34.3 | |
| Agentic | — | 2 | |
| Speed | 43.6 t/s | Best: 142 t/s | |
| TTFT | Best: 1.06 s | 2.29 s | |
| Input · $ / 1M tokens | $0.20 | — | |
| Output · $ / 1M tokens | $0.40 | — | |
| Context window | Best: 262K | 256K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3 30B A3B 2507 Instruct
- 7.5
- Devstral Small 2
- 7.5
Coding
- Qwen3 30B A3B 2507 Instruct
- —
- Devstral Small 2
- 29.3
Math
- Qwen3 30B A3B 2507 Instruct
- Best: 66.3
- Devstral Small 2
- 34.3
Agentic
- Qwen3 30B A3B 2507 Instruct
- —
- Devstral Small 2
- 2
Speed
- Qwen3 30B A3B 2507 Instruct
- 43.6 t/s
- Devstral Small 2
- Best: 142 t/s
TTFT
- Qwen3 30B A3B 2507 Instruct
- Best: 1.06 s
- Devstral Small 2
- 2.29 s
Input · $ / 1M tokens
- Qwen3 30B A3B 2507 Instruct
- $0.20
- Devstral Small 2
- —
Output · $ / 1M tokens
- Qwen3 30B A3B 2507 Instruct
- $0.40
- Devstral Small 2
- —
Context window
- Qwen3 30B A3B 2507 Instruct
- Best: 262K
- Devstral Small 2
- 256K
Reasoning
- Qwen3 30B A3B 2507 Instruct
- No
- Devstral Small 2
- No
Open weights
- Qwen3 30B A3B 2507 Instruct
- Yes
- Devstral Small 2
- 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 30B A3B 2507 Instruct7.5 · 43.6 t/s
- Devstral Small 27.5 · 142 t/s