A benchmark where AI models must run long algorithmic computations reveals a linear drop in accuracy as the log of reasoning steps increases, with top models scoring 7-16% on the hardest level.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LongReasonArena: A Long Reasoning Benchmark for Large Language Models
A benchmark where AI models must run long algorithmic computations reveals a linear drop in accuracy as the log of reasoning steps increases, with top models scoring 7-16% on the hardest level.