[KongchangAI]
Benchmark

Long Memo Val

A long-context memory evaluation benchmark used to measure the memory retention and retrieval capabilities of models or systems in long conversations or long texts.

Timeline (last 90 days)

Nov 7

In the Long Memo Val benchmark, Billion Context scored 79.2%, full context 83.2%, and the best RAG approach 62.6%, with cost reduced by 71%.

Unverified50%

All Facts (1)

Source Articles