Benchmark

LOCA-Bench (256k)

LOCA-Bench is a long-context agentic benchmark. The 256k variant evaluates agents using the official ReAct mode with an environment description length of…

Modality
text
Categories
reasoning, agents
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
MiniMax M3MiniMax0.4932026-06-01evidence

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.