HELM Classic - Entity Data Imputation: leaderboard
The "Entity Data Imputation" 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. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | mpt-30B | 85.52 | #1476 |
| 2 | Llama 2 13B | 84.36 | #1436 |
| 3 | LLaMA-30B | 84.36 | #1423 |
| 4 | text-davinci-002 | 84.16 | #1225 |
| 5 | text-davinci-003 | 83.91 | #1146 |
| 6 | Llama 2 70B | 83.77 | #1201 |
| 7 | GPT-3.5 Turbo (0613) | 83.59 | #1118 |
| 8 | falcon-7B Instruct | 83.59 | #1622 |
| 9 | davinci | 83.59 | #1553 |
| 10 | LLaMA-7B | 83.4 | #1564 |
| 11 | falcon-40B | 83.01 | #1442 |
| 12 | RedPajama-INCITE-Base-3B-v1 | 82.82 | #1618 |
| 13 | mpt-30B Instruct | 82.61 | #1470 |
| 14 | Palmyra X (43B) | 82.44 | #1317 |
| 15 | LLaMA-13B | 82.42 | #1516 |
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-entity-data-imputation · How It Works · Data refreshed daily, snapshot 2026-10-20.