Benchmark

GAIA2

GAIA2 evaluates general-purpose AI agents on real-world, multi-step questions that require reasoning, tool use, and information retrieval.

Modality
multimodal
Categories
reasoning, general, agents, tool_calling
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Muse Glimmer-30BMeta0.4332026-08-10evidence

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.