Yi-9B-Forest-DPO-v1.0: benchmark results

Provider: 01.AI. Released 2024-05-01. Access: Open.

Unified ELO 1487 ± 15, rank #1388 of 2928 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Medical LLM - MMLU College Medicine71.68Accuracy (%)96
Open LLM Leaderboard v1 - MMLU70.02Accuracy (%) (5-shot)93.2
Open Medical LLM - MMLU College Biology80.56Accuracy (%)88.6
Open Medical LLM - MMLU Clinical Knowledge75.09Accuracy (%)81.5
Open Medical LLM - PubMedQA75.8Accuracy (%)78.4
Open Medical LLM68.93Average Accuracy (%)63.9
Open Medical LLM - MMLU Medical Genetics79Accuracy (%)63.4
Open Medical-LLM Leaderboard68.93Medical average (%)63.3
Open Medical LLM - MMLU Professional Medicine72.06Accuracy (%)62.2
Open LLM Leaderboard v1 - GSM8K48.37Accuracy (%) (5-shot)61.6
Open Medical LLM - MMLU Anatomy62.96Accuracy (%)61.6
Open LLM Leaderboard v1 - WinoGrande76.87Accuracy (%) (5-shot)51.3

Interactive version: theaggregate.ai/model?slug=yi-9b-forest-dpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-23.