MentaLLaMA-chat-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1290 ± 33, rank #8865 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MentalBench (DSM Diagnosis) - Resolvable Differential Diagnosis | 25.98 | Accuracy (%) on the 13,050 Type 4 cases (cases that include | 42.9 |
| Open LLM Leaderboard v1 - GSM8K | 16.15 | Accuracy (%) (5-shot) | 37.9 |
| Open LLM Leaderboard v1 - HellaSwag | 76.1 | Normalized accuracy (%) (10-shot) | 28 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.82 | Normalized accuracy (%) (25-shot) | 27.9 |
| Open LLM Leaderboard v1 - MMLU | 47.51 | Accuracy (%) (5-shot) | 26.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.02 | MC2 (%) (0-shot) | 25.7 |
| Open LLM Leaderboard v1 - WinoGrande | 70.4 | Accuracy (%) (5-shot) | 24.7 |
| MentalBench (DSM Diagnosis) - Ambiguous Differential Diagnosis | 2.19 | Accuracy (%) on the 6,525 Type 3 cases (cases whose discrimi | 0 |
| MentalBench (DSM Diagnosis) - Complete Clinical Summaries | 30.9 | Accuracy (%) on the 1,725 Type 1 cases (structured professio | 0 |
| MentalBench (DSM Diagnosis) - Incomplete Patient Narratives | 30.67 | Accuracy (%) on the 3,450 Type 2 cases (colloquial patient s | 0 |
Interactive version: theaggregate.ai/model?slug=mentallama-chat-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.