Einstein-v4-phi2: benchmark results

Provider: Weyaxi. Access: Open.

Aggregate Rating 1367 ± 34, rank #7249 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K53.98Accuracy (%) (5-shot)65.7
Open LLM Leaderboard v1 - ARC Challenge59.98Normalized accuracy (%) (25-shot)45.8
Open LLM Leaderboard v1 - MMLU56.89Accuracy (%) (5-shot)40.2
Open LLM Leaderboard v1 - WinoGrande73.88Accuracy (%) (5-shot)33.9
Open LLM Leaderboard v1 - TruthfulQA MC245.8MC2 (%) (0-shot)32.3
Open LLM Leaderboard v1 - HellaSwag74.07Normalized accuracy (%) (10-shot)24.3

Interactive version: theaggregate.ai/model?slug=einstein-v4-phi2 · How It Works · Data refreshed daily, snapshot 2026-11-08.