OLMoE-1B-7B-0125-Instruct: benchmark results
Provider: Allen AI. Access: Open.
Unified ELO 1314 ± 57, rank #1437 of 1639 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 67.57 | Score | 80.1 |
| Open LLM Leaderboard - MATH Level 5 | 8.99 | Score | 44.2 |
| HELM Safety - Harm Bench | 62.91 | LM Evaluated Safety score | 29.1 |
| Open LLM Leaderboard - BBH | 38.25 | Score | 22.4 |
| Open LLM Leaderboard - MMLU-Pro | 19.15 | Score | 21 |
| Open LLM Leaderboard - MuSR | 36.36 | Score | 20.1 |
| Open LLM Leaderboard - GPQA | 26.01 | Score | 13.2 |
| HELM Safety - Xstest | 84.28 | LM Evaluated Safety score | 4.7 |
| HELM Safety - Anthropic Red Team | 88.94 | LM Evaluated Safety score | 3.5 |
| HELM Capabilities - IFEval | 62.85 | IFEval Strict Acc | 3 |
| HELM Safety - Safety Scenarios | 70.1 | Mean score | 2.3 |
| HELM Safety - Simple Safety Tests | 72.5 | LM Evaluated Safety score | 2.3 |
Interactive version: theaggregate.ai/model?slug=olmoe-1b-7b-0125-instruct · How It Works · Data refreshed daily, snapshot 2026-10-09.