ES-MemEval QA (RAG) - Temporal Reasoning: leaderboard

Metric: Token-level F1 (%; answers scored against human-checked reference answers; questions that order events and follow how they depend on each other over time; 236 questions; bge-m3 retrieval of the four most relevant full sessions from a FAISS index). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1GPT-4o27.6
2GPT-3.5 Turbo26.5
3Mistral Small 3.118.4
4Phi-3-medium-128k-instruct16.8
5Ministral-8B-Instruct-241013.3

Interactive version: theaggregate.ai/benchmark?slug=es-memeval-qa-rag-temporal-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-26.