APM-Bench
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
APM-Bench APM-Bench: Benchmarking cross-Session Persistent Memory for Real-World Egocentric Streaming Video Assistants Paper · Project page · Code APM-Bench groups egocentric video into activity-related trajectories that span separate interactions.
How to run
$ npm i -g lettokenburn-cli$ ltb bench info apm-bench
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
4 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Gemini 3.6 Flash | 53.5 | N/A | Independent | medium | Sep 29, 2026 | arxiv.org |
| Seed-2.0-Lite | 49.0 | N/A | Independent | medium | Sep 29, 2026 | arxiv.org |
| Qwen3.8 27B | 42.4 | N/A | Independent | medium | Sep 29, 2026 | arxiv.org |
| SimpleStream | 37.6 | N/A | Independent | medium | Sep 29, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsAbout
APM-Bench
APM-Bench: Benchmarking cross-Session Persistent Memory for Real-World Egocentric Streaming Video Assistants
Paper · Project page · Code
APM-Bench groups egocentric video into activity-related trajectories that span separate interactions. Its tasks test whether an assistant can use earlier experience while answering questions, perceiving the current scene, and deciding when to respond.
Dataset statistics
Video source Trajectories Sessions…