Healix-1.1B-V1-Chat-dDPO: benchmark results

Provider: Other. Released 2024-04-01. Access: Open.

Unified ELO 1203 ± 14, rank #2897 of 2928 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC241.55MC2 (%) (0-shot)17.4
Open Medical LLM - MMLU College Medicine25.43Accuracy (%)11.1
Open Medical LLM - MMLU Professional Medicine23.16Accuracy (%)10.2
Open LLM Leaderboard v1 - WinoGrande56.51Accuracy (%) (5-shot)9.9
Open LLM Leaderboard v1 - ARC Challenge30.55Normalized accuracy (%) (25-shot)9.6
Open LLM Leaderboard v1 - HellaSwag44.78Normalized accuracy (%) (10-shot)9
Open Medical LLM - MMLU Clinical Knowledge24.53Accuracy (%)7.1
Open Medical LLM - MMLU College Biology26.39Accuracy (%)6.8
Open Medical LLM - MMLU Anatomy22.22Accuracy (%)5.1
Open Medical LLM - MedQA (USMLE)26.71Accuracy (%)5.1
Open LLM Leaderboard v1 - GSM8K0Accuracy (%) (5-shot)4.6
Open LLM Leaderboard v1 - MMLU24.64Accuracy (%) (5-shot)4.6

Interactive version: theaggregate.ai/model?slug=healix-1-1b-v1-chat-ddpo · How It Works · Data refreshed daily, snapshot 2026-09-23.