Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | 20.1 | Best: 20.4 | |
| Math | — | 91.7 | |
| Speed | Best: 280 t/s | 133 t/s | |
| TTFT | Best: 1.49 s | 7.41 s | |
| Input · $ / 1M tokens | Best: $0.15 | $0.25×1.7 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.50 | $2×4 relative to the lowest price among the compared models | |
| Context window | Best: 1.02M | 400K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | $0.587 | — |
Intelligence
- Inkling 2 Mini
- 20.1
- GPT-5.1 Codex mini (High)
- Best: 20.4
Math
- Inkling 2 Mini
- —
- GPT-5.1 Codex mini (High)
- 91.7
Speed
- Inkling 2 Mini
- Best: 280 t/s
- GPT-5.1 Codex mini (High)
- 133 t/s
TTFT
- Inkling 2 Mini
- Best: 1.49 s
- GPT-5.1 Codex mini (High)
- 7.41 s
Input · $ / 1M tokens
- Inkling 2 Mini
- Best: $0.15
- GPT-5.1 Codex mini (High)
- $0.25×1.7 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Inkling 2 Mini
- Best: $0.50
- GPT-5.1 Codex mini (High)
- $2×4 relative to the lowest price among the compared models
Context window
- Inkling 2 Mini
- Best: 1.02M
- GPT-5.1 Codex mini (High)
- 400K
Reasoning
- Inkling 2 Mini
- Yes
- GPT-5.1 Codex mini (High)
- Yes
Open weights
- Inkling 2 Mini
- Yes
- GPT-5.1 Codex mini (High)
- No
Cost / task
- Inkling 2 Mini
- $0.587
- GPT-5.1 Codex mini (High)
- —
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.
- Inkling 2 Mini20.1 · 280 t/s
- GPT-5.1 Codex mini (High)20.4 · 133 t/s