Jamba 1.5 Large: benchmark results
AI21's 398B-total/94B-active hybrid SSM-Transformer MoE (August 2024) with a 256K effective context, released under the Jamba Open Model License. Provider: AI21 Labs. Released 2024-08-22. Access: API.
Aggregate Rating 1532 ± 19, rank #669 of 1656 rated models, from 146 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RULER | 96 | Avg Accuracy (%) | 100 |
| HELM Lite - LegalBench - PROA | 98.95 | Exact Match (%) | 92.2 |
| HELM MMLU - Sociology | 93.03 | EM | 86.5 |
| HELM Lite - OpenbookQA | 94.8 | Exact Match (%) | 85.6 |
| HELM MMLU - High School Geography | 93.94 | EM | 82.7 |
| HELM MMLU - Electrical Engineering | 79.31 | EM | 82.1 |
| HELM MMLU - High School Mathematics | 54.44 | EM | 81.4 |
| BenchTable - Utility | 68.7 | Weighted Score (%) | 80.8 |
| HELM MMLU - Moral Disputes | 84.97 | EM | 80.8 |
| HELM MMLU - High School Us History | 93.14 | EM | 79.5 |
| HELM MMLU - Philosophy | 84.89 | EM | 78.8 |
| HELM Lite - GSM8K | 84.6 | Exact Match (%) | 77.5 |
Interactive version: theaggregate.ai/model?slug=jamba-1-5-large · How It Works · Data refreshed daily, snapshot 2026-10-20.