[KongchangAI]
Benchmark

Context Bench

A context-management benchmark for coding agents that evaluates agent performance and cost efficiency on real codebase exploration tasks.

Timeline (last 90 days)

Nov 7

In the Context Bench benchmark run on DeepSeek V4.1 Flash, Billion Context scored an F1 of 0.31, exceeding full context's 0.29; the cost was $4.61, 58% lower than full context's $11.05.

Unverified50%

All Facts (1)

Source Articles