Marin 8B Instruct — benchmark results
Provider: Other. Released 2025-05-14. Access: Open.
Unified ELO 1349 ± 24, rank #1420 of 1776 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety HarmBench | 75.1 | LM Evaluated Safety score (%) | 53.5 |
| HELM Safety | 87 | Mean score (self-reported) | 27.3 |
| HELM Safety Anthropic Red Team | 97 | LM Evaluated Safety score (%) | 23.3 |
| HELM Safety SimpleSafetyTests | 95.8 | LM Evaluated Safety score (%) | 19.2 |
| HELM Safety XSTest | 91.7 | LM Evaluated Safety score (%) | 15.1 |
| HELM Capabilities - Omni-MATH | 15.95 | Acc | 14 |
| HELM Safety BBQ | 75.5 | BBQ accuracy (%) | 14 |
| HELM Capabilities - IFEval | 63.15 | IFEval Strict Acc | 6 |
| HELM Capabilities - MMLU-Pro | 18.8 | COT correct | 2 |
| HELM Capabilities - GPQA | 16.82 | COT correct | 0 |
| HELM Capabilities - WildBench | 47.71 | WB Score | 0 |
Interactive version: theaggregate.ai/model?slug=marin-8b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.