DeepSeek R1 (Jan '25)

MODEL RECORD: DPSK-DEEPSEEKR1JAN25

Organization
DeepSeek
Family
DEEPSEEKR1JAN25
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2025-01-20

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-008DEEPSEEKR1JAN25-001 DeepSeek R1 (Jan '25) Artificial Analysis Intelligence Index Overall 18.5 Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-002 DeepSeek R1 (Jan '25) GPQA Diamond Accuracy 70.8% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-003 DeepSeek R1 (Jan '25) Humanity's Last Exam No tools Overall 9.3% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-004 DeepSeek R1 (Jan '25) SciCode Overall 35.7% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-005 DeepSeek R1 (Jan '25) tau2-bench Overall 11.4% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-006 DeepSeek R1 (Jan '25) tau3-Banking Overall 6.4% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-007 DeepSeek R1 (Jan '25) Terminal-Bench Hard Overall 6.1% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-008 DeepSeek R1 (Jan '25) Terminal-Bench 2.1 Overall 19.1% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-009 DeepSeek R1 (Jan '25) CritPt Overall 0.6% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-010 DeepSeek R1 (Jan '25) AA-Omniscience Overall -31.3 Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-011 DeepSeek R1 (Jan '25) AA-Omniscience Accuracy 30.7% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-012 DeepSeek R1 (Jan '25) IFBench Overall 39% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-013 DeepSeek R1 (Jan '25) GDPval-AA Average Normalized Score 1.3% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKR1JAN25-014 DeepSeek R1 (Jan '25) AA-LCR Overall 52.3% Unknown Primary source DPSK-DEEPSEEKR1JAN25