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

BenchmarkScoreMetricPercentile
AI Chess Leaderboard (Continuation)481Elo33.3
BenchTable27.5Total Score (%)22.5
Vals AI LegalBench71.96Accuracy (%)22.4
AA MATH-50058Accuracy (%)19.8
AA SciCode18.4Accuracy (%)19.1
AA MMLU-Pro56.46Accuracy (%)18.3
AA LiveCodeBench17.25Pass@1 (%)18.1
AA GPQA Diamond38.69Accuracy (%)15.8
AI Chess Leaderboard (Reasoning)507Elo15.4
Artificial Analysis Intelligence Index5Intelligence Index15.1
Vals AI TaxEval v260.88Accuracy (%)14.5
AA Humanity's Last Exam3.97Accuracy (%)11.1

Interactive version: theaggregate.ai/model?slug=jamba-1-6-large · How the rankings work · Data refreshed daily, snapshot 2026-07-22.