Palmyra-X-004: benchmark results
Writer's enterprise frontier model emphasizing tool calling and built-in RAG for AI agents and workflows (October 2024). Provider: Writer. Released 2024-10-09. Access: API.
Unified ELO 1581 ± 1, rank #318 of 1392 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety XSTest | 98.4 | LM Evaluated Safety score (%) | 92.4 |
| HELM Lite | 85.05 | Mean win rate (self-reported) | 92.1 |
| HELM NaturalQuestions (Closed) | 45.66 | F1 (%) | 87.8 |
| HELM Safety SimpleSafetyTests | 100 | LM Evaluated Safety score (%) | 86 |
| HELM (Stanford) | 80.82 | Mean Win Rate (%) | 84.4 |
| HELM NarrativeQA | 77.26 | F1 (%) | 84.4 |
| HELM Capabilities - IFEval | 87.25 | IFEval Strict Acc | 82 |
| HELM NaturalQuestions (Open) | 75.38 | F1 (%) | 78.9 |
| HELM Safety BBQ | 95.5 | BBQ accuracy (%) | 70.9 |
| HELM Safety | 93.3 | Mean score (self-reported) | 64.5 |
| HELM WMT 2014 | 20.33 | BLEU-4 (%) | 62.8 |
| HELM Capabilities - WildBench | 80.2 | WB Score | 62 |
Interactive version: theaggregate.ai/model?slug=palmyra-x-004 · How It Works · Data refreshed daily, snapshot 2026-09-05.