HELM Classic - NarrativeQA — leaderboard
Metric: F1 (%). Source: crfm.stanford.edu. 66 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B | 76.99 |
| 2 | LLaMA-65B | 75.49 |
| 3 | LLaMA-30B | 75.25 |
| 4 | Llama 2 13B | 74.4 |
| 5 | mpt-30B | 73.15 |
| 6 | text-davinci-002 | 72.72 |
| 7 | text-davinci-003 | 72.71 |
| 8 | Mistral-7B-v0.1 | 71.65 |
| 9 | LLaMA-13B | 71.12 |
| 10 | Llama 2 7B | 69.12 |
| 11 | davinci | 68.69 |
| 12 | falcon-40B | 67.26 |
| 13 | LLaMA-7B | 66.91 |
| 14 | GPT-3.5 Turbo (0301) | 66.3 |
| 15 | GPT-3.5 Turbo (0613) | 62.51 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-narrativeqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.