Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Devstral Small 2
Mistral
- Qwen3 30B A3B 2507 Instruct
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Devstral Small 2 Mistral | Qwen3 30B A3B 2507 Instruct Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.5 | 7.5 | |
| Coding | 29.3 | — | |
| Math | 34.3 | Best: 66.3 | |
| Agentic | 2 | — | |
| Speed | Best: 142 t/s | 44.3 t/s | |
| TTFT | 2.29 s | Best: 1.05 s | |
| Input · $ / 1M tokens | — | $0.20 | |
| Output · $ / 1M tokens | — | $0.40 | |
| Context window | 256K | Best: 262K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Devstral Small 2
- 7.5
- Qwen3 30B A3B 2507 Instruct
- 7.5
Coding
- Devstral Small 2
- 29.3
- Qwen3 30B A3B 2507 Instruct
- —
Math
- Devstral Small 2
- 34.3
- Qwen3 30B A3B 2507 Instruct
- Best: 66.3
Agentic
- Devstral Small 2
- 2
- Qwen3 30B A3B 2507 Instruct
- —
Speed
- Devstral Small 2
- Best: 142 t/s
- Qwen3 30B A3B 2507 Instruct
- 44.3 t/s
TTFT
- Devstral Small 2
- 2.29 s
- Qwen3 30B A3B 2507 Instruct
- Best: 1.05 s
Input · $ / 1M tokens
- Devstral Small 2
- —
- Qwen3 30B A3B 2507 Instruct
- $0.20
Output · $ / 1M tokens
- Devstral Small 2
- —
- Qwen3 30B A3B 2507 Instruct
- $0.40
Context window
- Devstral Small 2
- 256K
- Qwen3 30B A3B 2507 Instruct
- Best: 262K
Reasoning
- Devstral Small 2
- No
- Qwen3 30B A3B 2507 Instruct
- No
Open weights
- Devstral Small 2
- Yes
- Qwen3 30B A3B 2507 Instruct
- 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.
- Devstral Small 27.5 · 142 t/s
- Qwen3 30B A3B 2507 Instruct7.5 · 44.3 t/s