Phi-4 Mini Instruct

MODEL RECORD: MSFT-PHI4MINIINSTRUCT

Organization
Microsoft
Family
PHI4MINIINSTRUCT
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2024-02-26

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-027PHI4MINIINSTRUCT-001 Phi-4 Mini Instruct Artificial Analysis Intelligence Index Overall 6 Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-002 Phi-4 Mini Instruct GPQA Diamond Accuracy 33.1% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-003 Phi-4 Mini Instruct Humanity's Last Exam No tools Overall 4.2% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-004 Phi-4 Mini Instruct SciCode Overall 10.8% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-005 Phi-4 Mini Instruct tau2-bench Overall 8.2% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-006 Phi-4 Mini Instruct tau3-Banking Overall 1% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-007 Phi-4 Mini Instruct Terminal-Bench Hard Overall 0% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-008 Phi-4 Mini Instruct Terminal-Bench 2.1 Overall 0.4% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-009 Phi-4 Mini Instruct CritPt Overall 0% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-010 Phi-4 Mini Instruct AA-Omniscience Overall -61 Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-011 Phi-4 Mini Instruct AA-Omniscience Accuracy 8.3% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-012 Phi-4 Mini Instruct IFBench Overall 21.1% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-013 Phi-4 Mini Instruct GDPval-AA Average Normalized Score 0% Unknown Primary source MSFT-PHI4MINIINSTRUCT
BR-027PHI4MINIINSTRUCT-014 Phi-4 Mini Instruct AA-LCR Overall 13.7% Unknown Primary source MSFT-PHI4MINIINSTRUCT