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

MMLU-Pro: Unspecified

Benchmark Family
MMLU-Pro
Version or Variant
Unknown
Canonical Reference
mmlu-pro/default
Release Date
Unknown
Status
ACTIVE

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-008V4FLASH-001 DeepSeek V4-Flash MMLU-Pro Exact Match 86.2 Unknown Primary source DPSK-V4FLASH
BR-008V4PRO-001 DeepSeek V4-Pro MMLU-Pro Exact Match 87.5 Unknown Primary source DPSK-V4PRO