HELM Long Context - RULER HotPotQA: leaderboard
HELM Long Context run of RULER HotPotQA, multi-hop question answering with long distractor contexts (string match).
Metric: RULER String Match. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 70 | #250 |
| 2 | GPT-4.1 Mini | 64 | #355 |
| 3 | Nova Premier | 57 | #437 |
| 4 | Gemini 2.0 Flash | 55 | #342 |
| 5 | Llama 4 Maverick Instruct FP8 | 55 | #414 |
| 6 | Gemini 2.0 Flash Lite | 53 | #450 |
| 7 | Llama 4 Scout Instruct | 47 | #539 |
| 8 | GPT-4.1 Nano | 41 | #731 |
| 9 | Nova Pro | 37 | #569 |
| 10 | Nova Lite | 35 | #754 |
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-ruler-hotpotqa · How It Works · Data refreshed daily, snapshot 2026-10-20.