Search operators

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

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

DeepSeek

Provider prefix
DPSK
Benchmark Record namespace
008

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-008DEEPSEEKV31-007 DeepSeek V3.1 CritPt Overall 2% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-008 DeepSeek V3.1 AA-Omniscience Overall -28.4 Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-009 DeepSeek V3.1 AA-Omniscience Accuracy 28.8% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-010 DeepSeek V3.1 IFBench Overall 41.5% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-011 DeepSeek V3.1 AA-LCR Overall 53.3% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-012 DeepSeek V3.1 Artificial Analysis Intelligence Index Overall 21 Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-013 DeepSeek V3.1 GPQA Diamond Accuracy 73.5% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-014 DeepSeek V3.1 Humanity's Last Exam No tools Overall 6.3% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-015 DeepSeek V3.1 SciCode Overall 36.7% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-016 DeepSeek V3.1 tau2-bench Overall 34.8% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-017 DeepSeek V3.1 Terminal-Bench Hard Overall 24.2% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-018 DeepSeek V3.1 CritPt Overall 0% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-019 DeepSeek V3.1 AA-Omniscience Overall -41.1 Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-020 DeepSeek V3.1 AA-Omniscience Accuracy 23.1% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-021 DeepSeek V3.1 IFBench Overall 37.8% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-022 DeepSeek V3.1 AA-LCR Overall 45% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31TERMINUS-001 DeepSeek V3.1 Terminus Artificial Analysis Intelligence Index Overall 30.4 Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-002 DeepSeek V3.1 Terminus GPQA Diamond Accuracy 79.2% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-003 DeepSeek V3.1 Terminus Humanity's Last Exam No tools Overall 15.2% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-004 DeepSeek V3.1 Terminus SciCode Overall 40.6% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-005 DeepSeek V3.1 Terminus tau2-bench Overall 37.1% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-006 DeepSeek V3.1 Terminus tau3-Banking Overall 15.9% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-007 DeepSeek V3.1 Terminus Terminal-Bench Hard Overall 30.3% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-008 DeepSeek V3.1 Terminus Terminal-Bench 2.1 Overall 44.9% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-009 DeepSeek V3.1 Terminus CritPt Overall 1.7% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-010 DeepSeek V3.1 Terminus AA-Omniscience Overall -24.3 Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-011 DeepSeek V3.1 Terminus AA-Omniscience Accuracy 27.9% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-012 DeepSeek V3.1 Terminus IFBench Overall 57% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-013 DeepSeek V3.1 Terminus GDPval-AA Average Normalized Score 19.5% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-014 DeepSeek V3.1 Terminus AA-LCR Overall 65% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-015 DeepSeek V3.1 Terminus Artificial Analysis Intelligence Index Overall 21.4 Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-016 DeepSeek V3.1 Terminus GPQA Diamond Accuracy 75.1% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-017 DeepSeek V3.1 Terminus Humanity's Last Exam No tools Overall 8.4% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-018 DeepSeek V3.1 Terminus SciCode Overall 32.1% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-019 DeepSeek V3.1 Terminus tau2-bench Overall 37.1% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-020 DeepSeek V3.1 Terminus Terminal-Bench Hard Overall 31.8% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-021 DeepSeek V3.1 Terminus CritPt Overall 0% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-022 DeepSeek V3.1 Terminus AA-Omniscience Overall -41.9 Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-023 DeepSeek V3.1 Terminus AA-Omniscience Accuracy 23.5% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-024 DeepSeek V3.1 Terminus IFBench Overall 41.2% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-025 DeepSeek V3.1 Terminus AA-LCR Overall 43.3% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV32-001 DeepSeek V3.2 Artificial Analysis Intelligence Index Overall 24.7 Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-002 DeepSeek V3.2 GPQA Diamond Accuracy 75.1% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-003 DeepSeek V3.2 Humanity's Last Exam No tools Overall 10.5% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-004 DeepSeek V3.2 SciCode Overall 38.7% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-005 DeepSeek V3.2 tau2-bench Overall 78.9% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-006 DeepSeek V3.2 Terminal-Bench Hard Overall 32.6% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-007 DeepSeek V3.2 CritPt Overall 0.9% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-008 DeepSeek V3.2 AA-Omniscience Overall -46.7 Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-009 DeepSeek V3.2 AA-Omniscience Accuracy 24.2% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-010 DeepSeek V3.2 IFBench Overall 49% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-011 DeepSeek V3.2 AA-LCR Overall 39% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-012 DeepSeek V3.2 Artificial Analysis Intelligence Index Overall 32 Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-013 DeepSeek V3.2 GPQA Diamond Accuracy 84% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-014 DeepSeek V3.2 Humanity's Last Exam No tools Overall 22.2% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-015 DeepSeek V3.2 SciCode Overall 38.9% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-016 DeepSeek V3.2 tau2-bench Overall 90.6% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-017 DeepSeek V3.2 tau3-Banking Overall 18.8% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-018 DeepSeek V3.2 Terminal-Bench Hard Overall 35.6% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-019 DeepSeek V3.2 Terminal-Bench 2.1 Overall 46.8% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-020 DeepSeek V3.2 CritPt Overall 2.9% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-021 DeepSeek V3.2 AA-Omniscience Overall -20.9 Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-022 DeepSeek V3.2 AA-Omniscience Accuracy 33.5% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-023 DeepSeek V3.2 IFBench Overall 60.7% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-024 DeepSeek V3.2 APEX-Agents Overall 14.5% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-025 DeepSeek V3.2 GDPval-AA Average Normalized Score 18.3% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-026 DeepSeek V3.2 AA-LCR Overall 65% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32EXP-001 DeepSeek V3.2 Exp Artificial Analysis Intelligence Index Overall 21.3 Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-002 DeepSeek V3.2 Exp GPQA Diamond Accuracy 73.8% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-003 DeepSeek V3.2 Exp Humanity's Last Exam No tools Overall 8.6% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-004 DeepSeek V3.2 Exp SciCode Overall 39.9% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-005 DeepSeek V3.2 Exp tau2-bench Overall 33.9% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-006 DeepSeek V3.2 Exp Terminal-Bench Hard Overall 25% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-007 DeepSeek V3.2 Exp CritPt Overall 1.4% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-008 DeepSeek V3.2 Exp AA-Omniscience Overall -47.1 Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-009 DeepSeek V3.2 Exp AA-Omniscience Accuracy 22.7% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-010 DeepSeek V3.2 Exp IFBench Overall 43.1% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-011 DeepSeek V3.2 Exp AA-LCR Overall 43% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-012 DeepSeek V3.2 Exp Artificial Analysis Intelligence Index Overall 25.4 Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-013 DeepSeek V3.2 Exp GPQA Diamond Accuracy 79.7% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-014 DeepSeek V3.2 Exp Humanity's Last Exam No tools Overall 13.8% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-015 DeepSeek V3.2 Exp SciCode Overall 37.7% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-016 DeepSeek V3.2 Exp tau2-bench Overall 33.9% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-017 DeepSeek V3.2 Exp Terminal-Bench Hard Overall 31.1% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-018 DeepSeek V3.2 Exp CritPt Overall 1.4% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-019 DeepSeek V3.2 Exp AA-Omniscience Overall -29.9 Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-020 DeepSeek V3.2 Exp AA-Omniscience Accuracy 28.2% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-021 DeepSeek V3.2 Exp IFBench Overall 54.1% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-022 DeepSeek V3.2 Exp AA-LCR Overall 69% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32SPECIALE-001 DeepSeek V3.2 Speciale Artificial Analysis Intelligence Index Overall 22.2 Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-002 DeepSeek V3.2 Speciale GPQA Diamond Accuracy 87.1% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-003 DeepSeek V3.2 Speciale Humanity's Last Exam No tools Overall 26.1% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-004 DeepSeek V3.2 Speciale SciCode Overall 44% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-005 DeepSeek V3.2 Speciale tau2-bench Overall 0% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-006 DeepSeek V3.2 Speciale Terminal-Bench Hard Overall 34.8% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-007 DeepSeek V3.2 Speciale CritPt Overall 7.4% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-008 DeepSeek V3.2 Speciale AA-Omniscience Overall -16.5 Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-009 DeepSeek V3.2 Speciale AA-Omniscience Accuracy 38.4% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-010 DeepSeek V3.2 Speciale IFBench Overall 63.9% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV32SPECIALE-011 DeepSeek V3.2 Speciale AA-LCR Overall 59.3% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE