Jamba 1.7 Mini: benchmark results
Provider: AI21 Labs. Released 2025-07-01. Access: API.
Unified ELO 1425 ± 1, rank #1048 of 1392 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Willingness (W/10) | 6.5 | W/10 Score | 62.5 |
| AA Omniscience - Software Engineering (SWE) - R | 10 | Accuracy (%) | 53.4 |
| AA Omniscience - Software Engineering (SWE) - Dart | 18 | Accuracy (%) | 51.5 |
| UGI - Natural Intelligence | 21.23 | NatInt Score | 47.1 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 46.1 |
| UGI Leaderboard | 32.85 | UGI Score | 42.3 |
| AA Omniscience - Law | 8.7 | Accuracy (%) | 30.5 |
| AA Omniscience - Software Engineering (SWE) - Go | 10 | Accuracy (%) | 28.2 |
| AA Omniscience - Humanities & Social Sciences | 14.2 | Accuracy (%) | 25.3 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 10 | Accuracy (%) | 24.6 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 10 | Accuracy (%) | 22.4 |
Interactive version: theaggregate.ai/model?slug=jamba-1-7-mini · How It Works · Data refreshed daily, snapshot 2026-09-05.