Pencil Puzzle Bench
Benchmark for evaluating AI models on multi-step verifiable reasoning using pencil puzzles.
Sign in to see this
Social posts and the rest of this product's in-depth data are open to signed-in readers.
Sign inBenchmark for evaluating AI models on multi-step verifiable reasoning using pencil puzzles.
Social posts and the rest of this product's in-depth data are open to signed-in readers.
Sign in