EverMemBench (Full Context) - Fine-Grained Recall (Single-Hop): leaderboard
Metric: Accuracy (%; whole multi-party dialogue history in context, open-ended, judged by an LLM). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 97.65 |
| 2 | GPT-4.1 Mini | 83.57 |
| 3 | Llama 4 Scout Instruct | 77.93 |
Interactive version: theaggregate.ai/benchmark?slug=evermembench-full-context-fine-grained-recall-single-hop · How It Works · Data refreshed daily, snapshot 2026-09-26.