Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Large 4 (High)
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Large 4 (High) Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 26 | Best: 26.1 | |
| Coding | 39.4 | — | |
| Agentic | 16.6 | — | |
| Cyber Index | — | 49.5% | |
| Speed | 151 t/s | Best: 161 t/s | |
| TTFT | Best: 0.86 s | 1.42 s | |
| Input · $ / 1M tokens | $5×7.1 relative to the lowest price among the compared models | Best: $0.70 | |
| Output · $ / 1M tokens | $30×14.3 relative to the lowest price among the compared models | Best: $2.10 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | Best: $0.569 | $2.06×3.6 relative to the lowest price among the compared models |
Intelligence
- GPT-5.5 Instant (June 2026)
- 26
- Mistral Large 4 (High)
- Best: 26.1
Coding
- GPT-5.5 Instant (June 2026)
- 39.4
- Mistral Large 4 (High)
- —
Agentic
- GPT-5.5 Instant (June 2026)
- 16.6
- Mistral Large 4 (High)
- —
Cyber Index
- GPT-5.5 Instant (June 2026)
- —
- Mistral Large 4 (High)
- 49.5%
Speed
- GPT-5.5 Instant (June 2026)
- 151 t/s
- Mistral Large 4 (High)
- Best: 161 t/s
TTFT
- GPT-5.5 Instant (June 2026)
- Best: 0.86 s
- Mistral Large 4 (High)
- 1.42 s
Input · $ / 1M tokens
- GPT-5.5 Instant (June 2026)
- $5×7.1 relative to the lowest price among the compared models
- Mistral Large 4 (High)
- Best: $0.70
Output · $ / 1M tokens
- GPT-5.5 Instant (June 2026)
- $30×14.3 relative to the lowest price among the compared models
- Mistral Large 4 (High)
- Best: $2.10
Context window
- GPT-5.5 Instant (June 2026)
- 1M
- Mistral Large 4 (High)
- 1M
Reasoning
- GPT-5.5 Instant (June 2026)
- Yes
- Mistral Large 4 (High)
- Yes
Open weights
- GPT-5.5 Instant (June 2026)
- No
- Mistral Large 4 (High)
- Yes
Cost / task
- GPT-5.5 Instant (June 2026)
- Best: $0.569
- Mistral Large 4 (High)
- $2.06×3.6 relative to the lowest price among the compared models
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-5.5 Instant (June 2026)26 · $0.569
- Mistral Large 4 (High)26.1 · $2.06