HELM Classic - OpenbookQA — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 32 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | text-davinci-003 | 64.6 |
| 2 | text-davinci-002 | 59.4 |
| 3 | davinci | 58.6 |
| 4 | gpt-neox-20B | 52.4 |
| 5 | gpt-j-6B | 51.4 |
| 6 | text-curie-001 | 51.4 |
| 7 | text-babbage-001 | 45.2 |
| 8 | text-ada-001 | 34.6 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-openbookqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.