Apps & Tools
S1Bench
A reasoning benchmark for AI models measuring decision-making accuracy.
byCuth
Is this your creation?
Playable
Description
S1Bench is a leaderboard that evaluates AI models on a battery of 1,999 typed decision questions. It measures macro accuracy to compare performance across frontier models including Perplexity Decider and SubQ Snap.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.