AGCI Benchmark Results: Dropstone Leads with 37.8% Cognitive Intelligence Score
We’ve officially benchmarked Dropstone against the AGCI Benchmark — a framework designed to evaluate adaptive and long-term cognitive intelligence in artificial systems.
Unlike traditional reasoning tests, AGCI measures how well systems learn, remember, and reason across sessions — essentially assessing continuity, adaptability, and persistent understanding.
Dropstone achieved an AGCI Cognitive Score of 37.8%, representing the highest measured performance so far relative to human baseline cognition (100%).
This milestone reflects Dropstone’s foundation as a self-learning IDE that builds persistent context and cognitive memory over time, allowing it to improve with every interaction.
The full benchmark and methodology are available here:
🔗 https://www.dropstone.io/research/agci-benchmark
Curious to hear your thoughts — how should we evolve AI benchmarks to better capture adaptive learning and cross-session reasoning in the coming years?
Replies
Triforce Todos
How does this score relate to actually saving time or fixing bugs faster?
Dropstone
@abod_rehman The score shows how much the system improves with use. Traditional models forget everything after each session, but Dropstone’s D2 Engine keeps learning from your workflow and builds understanding over time. As it adapts to your coding style, it starts predicting issues earlier, remembering past fixes, and reducing repeated effort. In practice, that means less time debugging and faster progress the more you use it.