AI21-Jamba-Mini-1.7 — benchmark results

Provider: Other. Access: Open.

Unified ELO 1449 ± 43, rank #985 of 1751 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Willingness (W/10)6.5W/10 Score62.1
UGI - Natural Intelligence21.23NatInt Score47.6
UGI Leaderboard32.85UGI Score42.7
UGI - Writing23.78Writing Score20
Hebrew LLM - Summarization (Pairwise)24.9Pairwise Score (%)12.9
Hebrew LLM - Trivia (0-shot)46.51Accuracy (%)9.7
Hebrew LLM - Nikud12.6Score (%)6.5
Hebrew LLM - Translation (Pairwise)2.76Pairwise Score (%)3.2
Hebrew LLM - Winograd (0-shot)67.27Accuracy (%)0

Interactive version: aibenchmarks.dev/model?slug=ai21-jamba-mini-1-7 · How the rankings work · Data refreshed daily, snapshot 2026-07-12.