Cinder-Phi-2-Test-1: benchmark results

Provider: Josephgflowers. Access: Open.

Aggregate Rating 1336 ± 35, rank #8047 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K42.53Accuracy (%) (5-shot)57.1
Open LLM Leaderboard v1 - ARC Challenge57.34Normalized accuracy (%) (25-shot)37.3
Open LLM Leaderboard v1 - WinoGrande73.8Accuracy (%) (5-shot)33.6
Open LLM Leaderboard v1 - MMLU50.81Accuracy (%) (5-shot)30.1
Open LLM Leaderboard v1 - TruthfulQA MC245.23MC2 (%) (0-shot)30.1
Open LLM Leaderboard v1 - HellaSwag72.6Normalized accuracy (%) (10-shot)23

Interactive version: theaggregate.ai/model?slug=cinder-phi-2-test-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.