YaLM (100B): benchmark results
Provider: Other.
Aggregate Rating 935 ± 47, rank #10916 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - LSAT | 23.04 | Exact Match (%) | 86.8 |
| HELM Classic - Dyck | 63.33 | Exact Match (%) | 69.1 |
| HELM Classic - Synthetic Reasoning Natural | 6.15 | F1 (%) | 27.9 |
| HELM Classic - TruthfulQA | 20.18 | Exact Match (%) | 25.8 |
| HELM Classic - BBQ | 32.8 | Exact Match (%) | 22 |
| HELM Classic - IMDB | 83.63 | Exact Match (%) | 15.2 |
| HELM Classic - LegalSupport | 48.4 | Exact Match (%) | 14 |
| HELM Classic - MMLU | 24.34 | Exact Match (%) | 13.6 |
| HELM Classic - BoolQ | 63.4 | Exact Match (%) | 12.1 |
| HELM Classic - bAbI | 34.58 | Exact Match (%) | 7.2 |
| HELM Classic - NarrativeQA | 25.21 | F1 (%) | 6.2 |
| HELM Classic - QuAC | 16.18 | F1 (%) | 4.6 |
Interactive version: theaggregate.ai/model?slug=yalm-100b · How It Works · Data refreshed daily, snapshot 2026-11-08.