02 / IT · Analysis
MoveBench joins public API benchmark tally
Benchmark counts and leaderboard entry counts measure different changes in the evaluation list.

The author of a DEV post announced the addition of MoveBench to a public API-based tally and three new entries across the Hugging Face leaderboards, an update relevant to developers choosing AI for game development.
The post covered official benchmark leaderboards on Hugging Face, a platform for sharing AI models and datasets. For game developers, the update describes a change in the available evaluation list.
The post distinguished a newly added benchmark from new leaderboard entries. That distinction also matters when reading the update: inclusion in a leaderboard and performance on a development task are separate considerations.
What the two counts measure
The DEV post reported 60 official benchmarks in the tally. This figure counts evaluations.
The post separately reported 1,392 leaderboard entries. Benchmark counts and entry counts therefore describe different units within the same tally.
Evidence for choosing game development AI
The DEV post identified MoveBench as the newly added official benchmark. That classification describes a change in the evaluation list; it does not establish performance on a game development task.
The post counted the three new entries across all leaderboards. For developers choosing AI for game development, the relevant basis for selection remains evaluation results suited to their work, rather than growth in registrations alone.