text-curie-001 — benchmark results

Provider: OpenAI. Released 2022-01-27. Access: API.

Unified ELO 1137 ± 28, rank #1748 of 1776 rated models, from 44 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HELM Classic - CNN/DailyMail15.16ROUGE-2 (%)79.3
HELM Classic - Entity Matching85.2Exact Match (%)75.8
HELM Classic - MS MARCO TREC50.72NDCG@10 (%)73.3
HELM Classic - Synthetic Reasoning Natural22.06F1 (%)66.2
HELM Classic - TruthfulQA25.74Exact Match (%)63.6
HELM Classic - MS MARCO Regular27.12RR@10 (%)62.1
HELM Classic - Entity Data Imputation79.13Exact Match (%)60.6
HELM Classic - QuAC35.79F1 (%)52.3
ToolBench - WebShop Long0Task Score44.2
HELM Classic - CivilComments53.73Exact Match (%)43.9
HELM Classic - Synthetic Reasoning Abstract18.99Exact Match (%)33.8
HELM Classic - IMDB92.27Exact Match (%)33.3

Interactive version: theaggregate.ai/model?slug=text-curie-001 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.