StarlingMaid-2x7B-base: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1437 ± 33, rank #4330 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU65.36Accuracy (%) (5-shot)84.1
Open LLM Leaderboard v1 - GSM8K65.88Accuracy (%) (5-shot)80.8
Open LLM Leaderboard v1 - ARC Challenge67.15Normalized accuracy (%) (25-shot)75.9
Open LLM Leaderboard v1 - TruthfulQA MC257.98MC2 (%) (0-shot)71.5
Open LLM Leaderboard v1 - WinoGrande79.79Accuracy (%) (5-shot)71
Open LLM Leaderboard v1 - HellaSwag85Normalized accuracy (%) (10-shot)70.9

Interactive version: theaggregate.ai/model?slug=starlingmaid-2x7b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.