MEME (In-Context) - Absence: leaderboard
Metric: Accuracy (fraction x 100; the whole ~35K-token episode transcript, 32K tokens of filler around the evidence sessions, fed to the answering model with no memory system; GPT-4o judge; absence: recognise that a dependent value is unknown after an upstream change with no rule). Source: arxiv.org. Saturation forecast: Around September 2027. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 35 |
| 2 | GPT-4.1 Mini | 4 |
Interactive version: theaggregate.ai/benchmark?slug=meme-in-context-absence · How It Works · Data refreshed daily, snapshot 2026-09-26.