OLMo-7B-Instruct: benchmark results
Provider: Allen AI. Released 2024-02-23. Access: Open.
Aggregate Rating 1285 ± 29, rank #8917 of 10916 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench Chat Hard | 50.66 | Accuracy (%) | 29.3 |
| BiGGen-Bench | 2.97 | Average Score (1-5) | 28.4 |
| RewardBench Chat | 89.66 | Accuracy (%) | 28.4 |
| RewardBench Safety | 64.86 | Accuracy (%) | 27.3 |
| RewardBench Reasoning | 71.68 | Accuracy (%) | 26.6 |
| RewardBench | 67.27 | Score (%) | 25.6 |
| RewardBench Prior Sets (0.5 weight) | 51.73 | Score (%) | 20.6 |
| BenchBench | 15.67 | Aggregate Score (%) | 14 |
| MixEval | 26.7 | Score | 5.9 |
| Chatbot Arena (Text - Business, Management & Financial Ops) | 1087 | Arena Score | 4.4 |
| Chatbot Arena (Text - Math) | 1053 | Arena Score | 3.5 |
| Chatbot Arena (Text - Multi-Turn) | 1042 | Arena Score | 3.5 |
Interactive version: theaggregate.ai/model?slug=olmo-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.