Compare / head-to-head
Jamba Large 1.7vsJamba2 3B
Jamba Large 1.7 and Jamba2 3B split their 2 shared benchmarks evenly. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 1
even split
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Providers
AI21 Labs
same provider
Jamba Large 1.7
AI21 Labs · released 2025-07-03
text
Jamba2 3B
AI21 Labs · released 2026-01-08
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 0 core
Quality
Benchmark matrix
2 shared · 0 only Jamba Large 1.7 · 2 only Jamba2 3B| Benchmark | Jamba Large 1.7 | Jamba2 3B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| FACTS | 83.2% ↗ | 54% ↗ | +29.2 pt | Jamba Large 1.7 |
| IFEval | 84% ↗ | 93% ↗ | -9 pt | Jamba2 3B |
| Only Jamba Large 1.7 reports · 0 | ||||
| Jamba Large 1.7 reports nothing Jamba2 3B does not. | ||||
| Only Jamba2 3B reports · 2 | ||||
| Collie | not reported | 24% ↗ | — | — |
| IFBench | not reported | 36% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Jamba Large 1.7 minus Jamba2 3B in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Jamba Large 1.7 | Jamba2 3B | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | 4K tokens | — | — |
| Input price / 1M | $2 ↗ | — | — |
| Output price / 1M | $8 ↗ | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $10 | — | — |
| Modalities | text | text | Tie |
| Released | 2025-07-03 | 2026-01-08 | — |
| Cited benchmark scores | 2 | 4 | — |
Reliability
AI21 Labs status
Live from /statusMore matchups
Jamba Large 1.7 vs …
Models sharing the most benchmarksMore matchups
Jamba2 3B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Jamba Large 1.7 and Jamba2 3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.