Jamba Mini 1.6: benchmark results
Provider: AI21 Labs. Released 2025-03-06. Access: API.
Unified ELO 1431 ± 1, rank #2183 of 3078 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Wolfram LLM Benchmarking Project | 33.2 | Correct Functionality (%) | 36.9 |
| AI for Education Pedagogy - Social studies | 61.82 | Accuracy (%) | 20.3 |
| AI for Education Pedagogy - Technology | 68.87 | Accuracy (%) | 19.3 |
| LegalBench | 69.73 | Score (%) | 17.2 |
| AI for Education Pedagogy | 61.07 | Accuracy (%) | 16.4 |
| AI for Education Pedagogy - Primary | 64.32 | Accuracy (%) | 16.4 |
| AI for Education Pedagogy - Secondary | 59.75 | Accuracy (%) | 15.6 |
| AI for Education Pedagogy - Maths | 53.97 | Accuracy (%) | 14.8 |
| AI for Education Pedagogy - Science | 57.38 | Accuracy (%) | 14.1 |
| AI for Education SEND | 60.55 | Accuracy (%) | 14.1 |
| MedQA | 52.52 | Score (%) | 4.3 |
| CorpFin v2 | 38.03 | Score (%) | 3.2 |
Interactive version: theaggregate.ai/model?slug=jamba-mini-1-6 · How It Works · Data refreshed daily, snapshot 2026-09-19.