vicuna-class-shishya-all-hal-7B-ep3: benchmark results

Provider: LMSYS. Access: Open.

Aggregate Rating 1301 ± 37, rank #8709 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU51.54Accuracy (%) (5-shot)30.8
Open LLM Leaderboard v1 - HellaSwag77.21Normalized accuracy (%) (10-shot)30.4
Open LLM Leaderboard v1 - TruthfulQA MC244.83MC2 (%) (0-shot)28.8
Open LLM Leaderboard v1 - WinoGrande71.03Accuracy (%) (5-shot)25.8
Open LLM Leaderboard v1 - ARC Challenge45.48Normalized accuracy (%) (25-shot)20.8
Open LLM Leaderboard v1 - GSM8K2.43Accuracy (%) (5-shot)20.1

Interactive version: theaggregate.ai/model?slug=vicuna-class-shishya-all-hal-7b-ep3 · How It Works · Data refreshed daily, snapshot 2026-11-08.