MaxiCPM-3x3B-Test: benchmark results

Provider: Other.

Aggregate Rating 1315 ± 38, rank #8428 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K44.88Accuracy (%) (5-shot)59
Open LLM Leaderboard v1 - MMLU52.88Accuracy (%) (5-shot)32.1
Open LLM Leaderboard v1 - HellaSwag71.74Normalized accuracy (%) (10-shot)21.9
Open LLM Leaderboard v1 - ARC Challenge45.99Normalized accuracy (%) (25-shot)21.2
Open LLM Leaderboard v1 - WinoGrande66.85Accuracy (%) (5-shot)20.8
Open LLM Leaderboard v1 - TruthfulQA MC241.06MC2 (%) (0-shot)16

Interactive version: theaggregate.ai/model?slug=maxicpm-3x3b-test · How It Works · Data refreshed daily, snapshot 2026-11-08.