sdoh-llama-3-3-70B: benchmark results
Provider: Other.
Aggregate Rating 1553 ± 43, rank #1661 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EPPCMinerBen (0-Shot) - Evidence Extraction | 73.42 | Micro-averaged F1 (%) of EPPC evidence extraction (the minim | 75 |
| EPPCMinerBen (1-Shot) - Code Classification | 63.85 | Micro-averaged F1 (%) of EPPC code classification (sentence- | 75 |
| EPPCMinerBen (2-Shot) - Code Classification | 64.68 | Micro-averaged F1 (%) of EPPC code classification (sentence- | 75 |
| EPPCMinerBen (0-Shot) - Code Classification | 63.6 | Micro-averaged F1 (%) of EPPC code classification (sentence- | 72.7 |
| EPPCMinerBen (1-Shot) - Evidence Extraction | 70.16 | Micro-averaged F1 (%) of EPPC evidence extraction (the minim | 66.7 |
| EPPCMinerBen (2-Shot) - Evidence Extraction | 70.05 | Micro-averaged F1 (%) of EPPC evidence extraction (the minim | 58.3 |
| EPPCMinerBen (2-Shot) - Subcode Classification | 42.5 | Micro-averaged F1 (%) of EPPC subcode classification (choosi | 58.3 |
| EPPCMinerBen (1-Shot) - Subcode Classification | 41.27 | Micro-averaged F1 (%) of EPPC subcode classification (choosi | 50 |
| EPPCMinerBen (0-Shot) - Subcode Classification | 40.8 | Micro-averaged F1 (%) of EPPC subcode classification (choosi | 36.4 |
Interactive version: theaggregate.ai/model?slug=sdoh-llama-3-3-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.