pandafish-7B [bfloat16] [rev: 8125718f8bc6]: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1428 ± 33, rank #4734 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU64.95Accuracy (%) (5-shot)79.1
Open LLM Leaderboard v1 - WinoGrande80.9Accuracy (%) (5-shot)76.2
Open LLM Leaderboard v1 - HellaSwag85.3Normalized accuracy (%) (10-shot)73.5
Open LLM Leaderboard v1 - ARC Challenge65.1Normalized accuracy (%) (25-shot)69.1
Open LLM Leaderboard v1 - GSM8K57.09Accuracy (%) (5-shot)69
Open LLM Leaderboard v1 - TruthfulQA MC252.61MC2 (%) (0-shot)56.8

Interactive version: theaggregate.ai/model?slug=pandafish-7b-bfloat16-rev-8125718f8bc6 · How It Works · Data refreshed daily, snapshot 2026-11-08.