Benchmark

GDPval-AA

GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.

Modality
text
Categories
legal, reasoning, finance, general, agents
Openness
unknown
Source
llm_stats
Reported scores
4

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemini 3.7 FlashGoogle1525.02026-08-13evidence
GLM-5.3Z.ai1769.02026-08-14evidence
Grok 4.6xAI1753.02026-08-12evidence
Inkling-SmallThinking Machines Lab1269.02026-07-30evidence

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.