Compare / head-to-head
Jamba2 3BvsJamba2 Mini
Jamba2 Mini leads 4 of 4 shared benchmarks. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 4
Jamba2 Mini leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Providers
AI21 Labs
same provider
Jamba2 3B
AI21 Labs · released 2026-01-08
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 0 core
Jamba2 Mini
AI21 Labs · released 2026-01-08
text
Quality
Benchmark matrix
4 shared · 0 only Jamba2 3B · 0 only Jamba2 Mini| Benchmark | Jamba2 3B | Jamba2 Mini | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| Collie | 24% ↗ | 33% ↗ | -9 pt | Jamba2 Mini |
| FACTS | 54% ↗ | 57% ↗ | -3 pt | Jamba2 Mini |
| IFBench | 36% ↗ | 38% ↗ | -2 pt | Jamba2 Mini |
| IFEval | 93% ↗ | 97% ↗ | -4 pt | Jamba2 Mini |
| Only Jamba2 3B reports · 0 | ||||
| Jamba2 3B reports nothing Jamba2 Mini does not. | ||||
| Only Jamba2 Mini reports · 0 | ||||
| Jamba2 Mini reports nothing Jamba2 3B does not. | ||||
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 Jamba2 3B minus Jamba2 Mini 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 | Jamba2 3B | Jamba2 Mini | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | 4K tokens | — |
| Input price / 1M | — | $0.2 ↗ | — |
| Output price / 1M | — | $0.4 ↗ | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $0.6 | — |
| Modalities | text | text | Tie |
| Released | 2026-01-08 | 2026-01-08 | — |
| Cited benchmark scores | 4 | 4 | — |
Reliability
AI21 Labs status
Live from /statusMore matchups
Jamba2 3B vs …
Models sharing the most benchmarksMore matchups
Jamba2 Mini vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Jamba2 3B and Jamba2 Mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.