ArmoRM-Llama3-8B-v0.1 — benchmark results
Provider: Other. Released 2024-05-23. Access: Open.
Unified ELO 1372 ± 57, rank #1334 of 1776 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Reasoning | 97.35 | Accuracy (%) | 93.5 |
| RewardBench Prior Sets (0.5 weight) | 74.29 | Score (%) | 93.3 |
| RewardBench | 88.6 | Score (%) | 88.6 |
| RewardBench Safety | 90.54 | Accuracy (%) | 86.1 |
| RewardBench Precise IF | 41.88 | Score (%) | 83.2 |
| RewardBench Chat | 96.93 | Accuracy (%) | 83 |
| RewardBench Math | 66.12 | Score (%) | 78.8 |
| RewardBench Chat Hard | 76.75 | Accuracy (%) | 75.6 |
| RewardBench Ties | 66.29 | Score (%) | 66.3 |
| Open Chinese LLM - TruthfulQA MC | 55.04 | Accuracy (%) | 61 |
| RewardBench Focus | 76.57 | Score (%) | 59.2 |
| StoryAlign | 49.7 | Average (self-reported) | 57.1 |
Interactive version: theaggregate.ai/model?slug=armorm-llama3-8b-v0-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.