Jamba 1.6 Mini — benchmark results
Provider: AI21 Labs. Released 2025-03-06. Access: API.
Unified ELO 1251 ± 62, rank #1614 of 1776 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 4.64 | Accuracy (%) | 25.8 |
| Vals AI LegalBench | 69.73 | Accuracy (%) | 17.6 |
| BenchTable | 17.6 | Total Score (%) | 12.8 |
| AA SciCode | 10.07 | Accuracy (%) | 10.2 |
| AA GPQA Diamond | 30 | Accuracy (%) | 7.5 |
| AA MMLU-Pro | 36.68 | Accuracy (%) | 5.5 |
| AA LiveCodeBench | 7.09 | Pass@1 (%) | 5 |
| Artificial Analysis Intelligence Index | 2.55 | Intelligence Index | 5 |
| AI Chess Leaderboard (Reasoning) | 430 | Elo | 4.7 |
| Vals AI MedQA | 52.52 | Accuracy (%) | 4.3 |
| AA MATH-500 | 25.67 | Accuracy (%) | 4 |
| Vals AI CorpFin v2 | 38.03 | Accuracy (%) | 3.3 |
Interactive version: theaggregate.ai/model?slug=jamba-1-6-mini · How the rankings work · Data refreshed daily, snapshot 2026-07-22.