RHELM (Long Context) - External Source: leaderboard
RHELM category (Zhang et al., Microsoft and Renmin University of China, 2026) that asks about the persona's documents and emails, including facts in attachments, reasoning and aggregation over tables, navigation by document structure, and counting or locating emails over a period. The model reads the whole history, dialogue and external documents in chronological order, in a 1M-token context; accuracy in percent on 249 questions judged 0 or 1 by an LLM, higher is better.
Metric: Accuracy (%; 249 external-source (attachment and email) questions, LLM judge, dialogue history plus external sources, full history in a 1M-token context). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 Mini | 43.4 | #775 |
| 2 | Gemini 2.5 Flash Lite | 19 | #958 |
| 3 | Qwen2.5-14B-Instruct-1M | 5.2 | #1417 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=rhelm-long-context-external-source · How It Works · Data refreshed daily, snapshot 2026-11-12.