cuckoo-starling-32k-7B: benchmark results

Provider: grimjim. Access: Open.

Aggregate Rating 1435 ± 34, rank #4403 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU64.88Accuracy (%) (5-shot)77.9
Open LLM Leaderboard v1 - HellaSwag85.97Normalized accuracy (%) (10-shot)77.7
Open LLM Leaderboard v1 - GSM8K62.77Accuracy (%) (5-shot)76.1
Open LLM Leaderboard v1 - ARC Challenge66.81Normalized accuracy (%) (25-shot)74.8
Open LLM Leaderboard v1 - TruthfulQA MC259.03MC2 (%) (0-shot)73.1
Open LLM Leaderboard v1 - WinoGrande80.11Accuracy (%) (5-shot)72.4

Interactive version: theaggregate.ai/model?slug=cuckoo-starling-32k-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.