Medichat-Llama3-8B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1422 ± 32, rank #5089 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.19 | Accuracy (%) (5-shot) | 82.8 |
| Open LLM Leaderboard v1 - GSM8K | 60.35 | Accuracy (%) (5-shot) | 72.4 |
| Open LLM Leaderboard v1 - WinoGrande | 78.93 | Accuracy (%) (5-shot) | 66.3 |
| Open LLM Leaderboard v1 - HellaSwag | 82.9 | Normalized accuracy (%) (10-shot) | 54.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.65 | MC2 (%) (0-shot) | 45.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.13 | Normalized accuracy (%) (25-shot) | 42.2 |
| RubRIX - General Caregiver Queries | 6 | Risk rate (% of the 29 RubRIX audit questions flagged per re | 40 |
| RubRIX - Dementia Caregiver Queries | 8 | Risk rate (% of the 29 RubRIX audit questions flagged per re | 20 |
Interactive version: theaggregate.ai/model?slug=medichat-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.