text-ada-001 — benchmark results

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

Unified ELO 1045 ± 32, rank #1769 of 1776 rated models, from 34 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HELM Classic - LSAT21.3Exact Match (%)66.9
HELM Classic - BBQ35.9Exact Match (%)52.4
HELM Classic - TruthfulQA23.19Exact Match (%)49.2
HELM Classic - Entity Matching80.85Exact Match (%)48.5
HELM Classic - CNN/DailyMail13.56ROUGE-2 (%)45.1
HELM Classic - LegalSupport51.47Exact Match (%)41.9
HELM Classic - Synthetic Reasoning Natural14.53F1 (%)41.2
HELM Classic - XSUM3.44ROUGE-2 (%)12.2
HELM Classic - IMDB82.2Exact Match (%)12.1
HELM Classic - CivilComments50.33Exact Match (%)10.6
HELM Classic - MATH2.04Equivalent (%)10.3
HELM Classic - MS MARCO TREC30.16NDCG@10 (%)10

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