Benchmark

ProfBench

ProfBench evaluates models on professional-domain reasoning and knowledge-work tasks, including search-augmented question answering across expert fields.

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

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Nemotron 3 Ultra (550B A55B)NVIDIA0.562026-06-04evidence

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.