HELM Classic - OpenbookQA: leaderboard
The "OpenbookQA" subtask of HELM Classic. A scenario from Stanford HELM Classic, the holistic evaluation suite scoring language models across accuracy, robustness and calibration on a broad set of tasks.
Metric: Exact Match (%). Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 32 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | text-davinci-003 | 64.6 | #1146 |
| 2 | text-davinci-002 | 59.4 | #1225 |
| 3 | OPT-175B | 58.6 | #1538 |
| 4 | davinci | 58.6 | #1553 |
| 5 | OPT-66B | 53.4 | #1603 |
| 6 | gpt-neox-20B | 52.4 | #1600 |
| 7 | gpt-j-6B | 51.4 | #1609 |
| 8 | text-curie-001 | 51.4 | #1632 |
| 9 | text-babbage-001 | 45.2 | #1648 |
| 10 | text-ada-001 | 34.6 | #1655 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-openbookqa · How It Works · Data refreshed daily, snapshot 2026-10-20.