AI21 Labs model product
5 family, a state-of-the-art hybrid SSM-Transformer instruction following foundation model offering superior long context handling, speed, and quality.
Updated Aug 17, 2026. Default version: Jamba 1.5 Mini
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Jamba 1.5 Mini.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkWild Bench | Score42.4% | Rank08 | Participants8 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score85.7% | Rank13 | Participants34 | Percentile63.6% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score54.1% | Rank15 | Participants18 | Percentile17.6% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score46.1% | Rank20 | Participants26 | Percentile24.0% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score75.8% | Rank41 | Participants48 | Percentile14.9% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score69.7% | Rank84 | Participants101 | Percentile17.0% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score42.5% | Rank127 | Participants134 | Percentile5.3% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score32.3% | Rank225 | Participants239 | Percentile5.9% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryoverall | Rank298 | Rating / score1239.6 | Votes8,858 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank299 | Rating / score1186.8 | Votes8,858 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Jamba 1.5 Mini. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderBedrock | Output Speed100 tok/s | Catalog Latency0.5 s | Max Input256.1K | Max Output256.1K | Updated |
| ProviderGoogle | Output Speed100 tok/s | Catalog Latency0.3 s | Max Input256.1K | Max Output256.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionJamba 1.5 Mini | Released | LLMBoard0.0 | Parameters52B | Context256.1K | Max output256.1K | Open weightsNo | LicenseJamba Open Model License |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Jamba 1.5 Mini and its available data.
5 family, a state-of-the-art hybrid SSM-Transformer instruction following foundation model offering superior long context handling, speed, and quality.
Data as of 2026-08-17.
Common questions about Jamba 1.5 Mini.
Jamba 1.5 Mini's default version was released on Aug 22, 2024.
No official standard PAYG price is currently available for Jamba 1.5 Mini.
Jamba 1.5 Mini was created by AI21 Labs.
The default version has a 256.1K token context window.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.
Nearby ranked alternatives include IBM Granite 4.0 Tiny, Llama 3.2 11B, Shieldstral 1.0.