MBX-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1465 ± 41, rank #3053 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K71.27Accuracy (%) (5-shot)95.5
Open LLM Leaderboard v1 - ARC Challenge72.87Normalized accuracy (%) (25-shot)94
Open LLM Leaderboard v1 - HellaSwag88.38Normalized accuracy (%) (10-shot)91.4
Open LLM Leaderboard v1 - WinoGrande83.66Accuracy (%) (5-shot)90.1
Open LLM Leaderboard v1 - TruthfulQA MC269.11MC2 (%) (0-shot)88.5
Open LLM Leaderboard v1 - MMLU64.93Accuracy (%) (5-shot)78.8

Interactive version: theaggregate.ai/model?slug=mbx-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.