HELM Long Context - InfiniteBench En.Sum: leaderboard
HELM Long Context run of InfiniteBench English summarization over book-length inputs, scored by ROUGE-L.
Metric: ROUGE-L. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 4 Scout Instruct | 17.6 | #539 |
| 2 | GPT-4.1 (2025-04-14) | 17.38 | #250 |
| 3 | Llama 4 Maverick Instruct FP8 | 16.06 | #414 |
| 4 | GPT-4.1 Mini | 16.05 | #355 |
| 5 | Gemini 2.0 Flash Lite | 15.51 | #450 |
| 6 | Gemini 2.0 Flash | 15.11 | #342 |
| 7 | Nova Lite | 14.76 | #754 |
| 8 | Nova Premier | 13.72 | #437 |
| 9 | GPT-4.1 Nano | 11.34 | #731 |
| 10 | Nova Pro | 10.95 | #569 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-long-context-infinitebench-en-sum · How It Works · Data refreshed daily, snapshot 2026-10-20.