BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

GPQA

Benchmark Family
GPQA
Organization
New York University
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedgpqa/defaultACTIVE1
Diamondgpqa/diamondACTIVE405

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-048MOTIF2127BREASONING-002 Motif-2-12.7B-Reasoning GPQA Diamond Accuracy 69.5% Unknown Primary source MOTIF-MOTIF2127BREASONING
BR-049NANBEIGE413B-002 Nanbeige4.1-3B GPQA Diamond Accuracy 84.9% Unknown Primary source NANB-NANBEIGE413B
BR-051TRINITYLARGETHINKING-002 Trinity Large Thinking GPQA Diamond Accuracy 75.2% Unknown Primary source ARCEE-TRINITYLARGETHINKING
BR-052FALCONH1R7B-002 Falcon-H1R-7B GPQA Diamond Accuracy 66.1% Unknown Primary source TIIUA-FALCONH1R7B
BR-053COGITOV21-001 Cogito v2.1 GPQA Diamond Accuracy 76.8% Unknown Primary source DPCOG-COGITOV21
BR-054OPENCHAT351210-002 OpenChat 3.5 (1210) GPQA Diamond Accuracy 23% Unknown Primary source OPCHT-OPENCHAT351210