Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Jamba 1.6 Large
AI21 Labs
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Jamba 1.6 Large AI21 Labs | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 6 | 6 | |
| Math | — | 13.7 | |
| Speed | — | 14.4 t/s | |
| TTFT | — | 35.5 s | |
| Input · $ / 1M tokens | — | $0.060 | |
| Output · $ / 1M tokens | — | $0.25 | |
| Context window | Best: 256K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Jamba 1.6 Large
- 6
- Granite 4.0 H Small
- 6
Math
- Jamba 1.6 Large
- —
- Granite 4.0 H Small
- 13.7
Speed
- Jamba 1.6 Large
- —
- Granite 4.0 H Small
- 14.4 t/s
TTFT
- Jamba 1.6 Large
- —
- Granite 4.0 H Small
- 35.5 s
Input · $ / 1M tokens
- Jamba 1.6 Large
- —
- Granite 4.0 H Small
- $0.060
Output · $ / 1M tokens
- Jamba 1.6 Large
- —
- Granite 4.0 H Small
- $0.25
Context window
- Jamba 1.6 Large
- Best: 256K
- Granite 4.0 H Small
- 128K
Reasoning
- Jamba 1.6 Large
- No
- Granite 4.0 H Small
- No
Open weights
- Jamba 1.6 Large
- Yes
- Granite 4.0 H Small
- 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.
- Granite 4.0 H Small6 · $0.107
Not plotted for lack of data on these axes: Jamba 1.6 Large.