Jamba 1.7 Mini — benchmark results
Provider: AI21 Labs. Released 2025-07-01. Access: API.
Unified ELO 1360 ± 44, rank #1380 of 1776 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Willingness (W/10) | 6.5 | W/10 Score | 62.1 |
| AA Omniscience - Software Engineering (SWE) - Dart | 20 | Accuracy (%) | 47.9 |
| UGI - Natural Intelligence | 21.23 | NatInt Score | 47.6 |
| AA Omniscience - Software Engineering (SWE) - R | 10 | Accuracy (%) | 45.4 |
| UGI Leaderboard | 32.85 | UGI Score | 42.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 37.3 |
| AA-LCR | 12.7 | Score (self-reported) | 31.5 |
| AA Omniscience - Law | 8.6 | Accuracy (%) | 31 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA Omniscience - Humanities & Social Sciences | 14.6 | Accuracy (%) | 26.3 |
| AA Long Context Reasoning | 12.67 | Accuracy (%) | 24 |
Interactive version: theaggregate.ai/model?slug=jamba-1-7-mini · How the rankings work · Data refreshed daily, snapshot 2026-07-22.