AI21 LabsAuto-detectedJamba Large 1.6
Best configuration ranks #609 of 610 on the BenchLeader Index at 25.2 ±7.9. Last measured 1 Sept 2026.
- Blended price
- $3.50/M
- $2.00 in · $8.00 out
- Output speed
- –
- First answer
- –
- Context
- 256k
- Overall index25
- Coding10
- Maths17
- Knowledge21
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (Vals)not in index | 36.1%#124 | Vals AI |
Coding
| Benchmark | default | Source |
|---|---|---|
| LiveCodeBench | 22.3%#133 | Vals AI |
Maths
| Benchmark | default | Source |
|---|---|---|
| AIME (Vals) | 0.4%#90 | Vals AI |
| MGSM | 71.2%#68 | Vals AI |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0032 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.029 | – | – |
| Code edit | 6,000 / 1,500 | $0.024 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.152 | – | – |
| Structured extraction | 2,000 / 200 | $0.0056 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.