Benchmark

AutoLogi

AutoLogi is an automated method for synthesizing open-ended logic puzzles to evaluate reasoning abilities of Large Language Models. The benchmark…

Modality
text
Categories
reasoning
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Kimi K2 InstructMoonshot AI0.8952025-07-11evidence
Kimi K2-Instruct-0905Moonshot AI0.8952025-09-05evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.