HELM Classic - Entity Data Imputation — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | mpt-30B | 85.52 |
| 2 | LLaMA-30B | 84.36 |
| 3 | Llama 2 13B | 84.36 |
| 4 | text-davinci-002 | 84.16 |
| 5 | text-davinci-003 | 83.91 |
| 6 | Llama 2 70B | 83.77 |
| 7 | GPT-3.5 Turbo (0613) | 83.59 |
| 8 | davinci | 83.59 |
| 9 | LLaMA-7B | 83.4 |
| 10 | falcon-40B | 83.01 |
| 11 | LLaMA-13B | 82.42 |
| 12 | LLaMA-65B | 82.24 |
| 13 | Llama 2 7B | 80.1 |
| 14 | Mistral-7B-v0.1 | 79.52 |
| 15 | text-curie-001 | 79.13 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-entity-data-imputation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.