Jallabi-34B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1540 ± 20, rank #941 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU76.4Accuracy (%) (5-shot)97.4
Open LLM Leaderboard - MuSR48.22Score95.3
Open LLM Leaderboard - MMLU-Pro46.82Score85.8
Open LLM Leaderboard - GPQA33.89Score84.1
Open LLM Leaderboard - BBH60.23Score82.2
Open LLM Leaderboard v1 - GSM8K65.2Accuracy (%) (5-shot)79.6
Open LLM Leaderboard v1 - WinoGrande81.45Accuracy (%) (5-shot)79.3
Open LLM Leaderboard v1 - ARC Challenge66.04Normalized accuracy (%) (25-shot)72.1
Open LLM Leaderboard v1 - HellaSwag83.81Normalized accuracy (%) (10-shot)61.7
Open LLM Leaderboard v1 - TruthfulQA MC251.46MC2 (%) (0-shot)52
Open LLM Leaderboard - IFEval35.29Score33.8
Open LLM Leaderboard - MATH Level 55.21Score29.1

Interactive version: theaggregate.ai/model?slug=jallabi-34b · How It Works · Data refreshed daily, snapshot 2026-09-23.