Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5 nano (Minimal)
OpenAI
- Mistral Small 3.1
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5 nano (Minimal) OpenAI | Mistral Small 3.1 Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.1 | 7.1 | |
| Coding | — | 26.3 | |
| Math | Best: 27.3 | 3.7 | |
| Agentic | — | 1.2 | |
| Speed | Best: 141 t/s | 27.8 t/s | |
| TTFT | Best: 0.76 s | 0.93 s | |
| Input · $ / 1M tokens | Best: $0.050 | $0.080×1.6 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | $0.40×3 relative to the lowest price among the compared models | Best: $0.135 | |
| Context window | Best: 400K | 128K | |
| Reasoning | No | No | |
| Open weights | No | Yes | |
| Cost / task | — | $0.0255 |
Intelligence
- GPT-5 nano (Minimal)
- 7.1
- Mistral Small 3.1
- 7.1
Coding
- GPT-5 nano (Minimal)
- —
- Mistral Small 3.1
- 26.3
Math
- GPT-5 nano (Minimal)
- Best: 27.3
- Mistral Small 3.1
- 3.7
Agentic
- GPT-5 nano (Minimal)
- —
- Mistral Small 3.1
- 1.2
Speed
- GPT-5 nano (Minimal)
- Best: 141 t/s
- Mistral Small 3.1
- 27.8 t/s
TTFT
- GPT-5 nano (Minimal)
- Best: 0.76 s
- Mistral Small 3.1
- 0.93 s
Input · $ / 1M tokens
- GPT-5 nano (Minimal)
- Best: $0.050
- Mistral Small 3.1
- $0.080×1.6 relative to the lowest price among the compared models
Output · $ / 1M tokens
- GPT-5 nano (Minimal)
- $0.40×3 relative to the lowest price among the compared models
- Mistral Small 3.1
- Best: $0.135
Context window
- GPT-5 nano (Minimal)
- Best: 400K
- Mistral Small 3.1
- 128K
Reasoning
- GPT-5 nano (Minimal)
- No
- Mistral Small 3.1
- No
Open weights
- GPT-5 nano (Minimal)
- No
- Mistral Small 3.1
- Yes
Cost / task
- GPT-5 nano (Minimal)
- —
- Mistral Small 3.1
- $0.0255
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.
- GPT-5 nano (Minimal)7.1 · $0.138
- Mistral Small 3.17.1 · $0.094