Jamba 1.6 Large — benchmark results
Provider: AI21 Labs. Released 2025-03-06. Access: API.
Unified ELO 1369 ± 57, rank #1347 of 1776 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Chess Leaderboard (Continuation) | 481 | Elo | 33.3 |
| BenchTable | 27.5 | Total Score (%) | 22.5 |
| Vals AI LegalBench | 71.96 | Accuracy (%) | 22.4 |
| AA MATH-500 | 58 | Accuracy (%) | 19.8 |
| AA SciCode | 18.4 | Accuracy (%) | 19.1 |
| AA MMLU-Pro | 56.46 | Accuracy (%) | 18.3 |
| AA LiveCodeBench | 17.25 | Pass@1 (%) | 18.1 |
| AA GPQA Diamond | 38.69 | Accuracy (%) | 15.8 |
| AI Chess Leaderboard (Reasoning) | 507 | Elo | 15.4 |
| Artificial Analysis Intelligence Index | 5 | Intelligence Index | 15.1 |
| Vals AI TaxEval v2 | 60.88 | Accuracy (%) | 14.5 |
| AA Humanity's Last Exam | 3.97 | Accuracy (%) | 11.1 |
Interactive version: theaggregate.ai/model?slug=jamba-1-6-large · How the rankings work · Data refreshed daily, snapshot 2026-07-22.