DeepSeek V3 (Dec '24)

MODEL RECORD: DPSK-DEEPSEEKV3DEC24

Organization
DeepSeek
Family
DEEPSEEKV3DEC24
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2024-12-26

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-008DEEPSEEKV3DEC24-001 DeepSeek V3 (Dec '24) Artificial Analysis Intelligence Index Overall 14.2 Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-002 DeepSeek V3 (Dec '24) GPQA Diamond Accuracy 55.7% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-003 DeepSeek V3 (Dec '24) Humanity's Last Exam No tools Overall 3.6% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-004 DeepSeek V3 (Dec '24) SciCode Overall 35.4% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-005 DeepSeek V3 (Dec '24) tau2-bench Overall 22.8% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-006 DeepSeek V3 (Dec '24) tau3-Banking Overall 4.7% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-007 DeepSeek V3 (Dec '24) Terminal-Bench Hard Overall 6.8% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-008 DeepSeek V3 (Dec '24) Terminal-Bench 2.1 Overall 16.9% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-009 DeepSeek V3 (Dec '24) CritPt Overall 0% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-010 DeepSeek V3 (Dec '24) AA-Omniscience Overall -41.3 Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-011 DeepSeek V3 (Dec '24) AA-Omniscience Accuracy 25.4% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-012 DeepSeek V3 (Dec '24) IFBench Overall 34.8% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-013 DeepSeek V3 (Dec '24) GDPval-AA Average Normalized Score 0% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV3DEC24-014 DeepSeek V3 (Dec '24) AA-LCR Overall 29% Unknown Primary source DPSK-DEEPSEEKV3DEC24