Jamba-v0.1 — benchmark results
AI21's Apache-2.0 hybrid Mamba-Transformer MoE (52B total/12B active), the first production-grade SSM-based model, with a 256K context. Provider: AI21 Labs. Released 2024-03-28. Access: API.
Unified ELO 1464 ± 15, rank #936 of 1776 rated models, from 108 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Swedish NLU - Swerec | 81.11 | Sentiment classification Score (%) | 99.8 |
| EuroEval German NLU - Germanquad | 64.59 | Reading comprehension Score (%) | 88.4 |
| EuroEval Icelandic NLU - NQII | 55.84 | Reading comprehension Score (%) | 86.9 |
| EuroEval Finnish NLU - Tydiqa FI | 71.08 | Reading comprehension Score (%) | 85.9 |
| EuroEval Dutch NLU - DBRD | 91.36 | Sentiment classification Score (%) | 85.7 |
| EuroEval Portuguese NLU - SST-2 PT | 83.67 | Sentiment classification Score (%) | 85.5 |
| EuroEval Finnish NLU - Scandisent FI | 92.03 | Sentiment classification Score (%) | 84.8 |
| EuroEval French NLU - FQuAD | 71.56 | Reading comprehension Score (%) | 83.6 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 74.65 | Reading comprehension Score (%) | 83.2 |
| EuroEval Portuguese NLU - ScaLA PT | 26.68 | Linguistic acceptability Score (%) | 81.4 |
| EuroEval Portuguese NLU | 56.3 | NLU Average Score (%) | 79.7 |
| EuroEval Spanish NLU - MLQA ES | 64.33 | Reading comprehension Score (%) | 78.5 |
Interactive version: theaggregate.ai/model?slug=jamba-v0-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.