text-babbage-001 — benchmark results
Provider: OpenAI. Released 2022-01-27. Access: API.
Unified ELO 1102 ± 30, rank #1761 of 1776 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - CNN/DailyMail | 15.11 | ROUGE-2 (%) | 75.6 |
| HELM Classic - Synthetic Reasoning Natural | 21.16 | F1 (%) | 61.8 |
| HELM Classic - MS MARCO TREC | 44.92 | NDCG@10 (%) | 56.7 |
| HELM Classic - BBQ | 35.9 | Exact Match (%) | 52.4 |
| HELM Classic - TruthfulQA | 23.29 | Exact Match (%) | 51.5 |
| HELM Classic - LegalSupport | 51.74 | Exact Match (%) | 46.3 |
| HELM Classic - Entity Matching | 73.36 | Exact Match (%) | 42.4 |
| HELM Classic - MS MARCO Regular | 20.76 | RR@10 (%) | 41.4 |
| HELM Classic - LSAT | 18.99 | Exact Match (%) | 33.1 |
| HELM Classic - IMDB | 91.27 | Exact Match (%) | 28.8 |
| HELM Classic - RAFT | 50.91 | Exact Match (%) | 22.7 |
| HELM Classic - Entity Data Imputation | 70.4 | Exact Match (%) | 21.2 |
Interactive version: theaggregate.ai/model?slug=text-babbage-001 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.