AI21 LabsJamba Mini 1.6
Jamba Mini 1.6 is an AI21 Labs proprietary model. Its best configuration ranks #785 of 785 on the BenchLeader Index at 21.8 ±7.1, in the lower half. The ± is the point: 1 other configuration scores within that range, so it and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (16) and lowest in coding (5). At $0.250 per million tokens blended it is cheaper than most ranked models. Last measured 13 Oct 2026.
- Blended price
- $0.250/M
- $0.200 in · $0.400 out
- Output speed
- –
- First answer
- –
- Context
- 256k
- Full answer
- –
- Cost per run
- –
- Released
- –
- date not published by our sources
- Overall index22
- Coding5
- Maths13
- Knowledge16
Versions
AI21 Labs has shipped 5 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Jamba Mini | 8 Jan 2026 | – | – |
| Jamba 1.7 Mini | 7 Jul 2025 | 39.5 | #685 |
| Jamba 1.5 Mini | 22 Aug 2024 | 37.3 | #734 |
| Jamba Mini 1.6this page | – | 21.8 | #785 |
| Jamba Mini 1.7 | – | – | – |
Benchmark results
See all LLM benchmarks. 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 | not stated | Source |
|---|---|---|
| GPQA Diamond (Vals)not in index | 32.1%#127 | Vals AI |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| LiveCodeBench | 9.9%#137 | Vals AI |
Maths
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 | $0.0002 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0026 | – | – |
| Code edit | 6,000 / 1,500 | $0.0018 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.014 | – | – |
| Structured extraction | 2,000 / 200 | $0.0005 | – | – |
More from AI21 Labs
See also
Questions people ask
- What are Jamba Mini 1.6's benchmark scores?
- As of 25 Oct 2026, Jamba Mini 1.6 scores 21.8 ±7.1 on the BenchLeader Index, strongest in knowledge (16) and weakest in coding (5). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Jamba Mini 1.6 rank?
- Jamba Mini 1.6 is #785 of 785 ranked configurations on 25 Oct 2026. 1 other configuration scores within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Jamba Mini 1.6 cost per 1M tokens?
- As of 25 Oct 2026, Jamba Mini 1.6 costs $0.200 per 1M input tokens and $0.400 per 1M output tokens, $0.250 blended (three input tokens per output token).
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Jamba Mini 1.6: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/jamba-mini-1-6.