KwaiKAT

Provider prefix
KWAI
Benchmark Record namespace
040

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-040KATCODERPROV1-001 KAT-Coder-Pro V1 Artificial Analysis Intelligence Index Overall 34.6 Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-002 KAT-Coder-Pro V1 GPQA Diamond Accuracy 76.4% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-003 KAT-Coder-Pro V1 Humanity's Last Exam No tools Overall 33.4% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-004 KAT-Coder-Pro V1 SciCode Overall 36.6% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-005 KAT-Coder-Pro V1 tau2-bench Overall 88.6% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-006 KAT-Coder-Pro V1 tau3-Banking Overall 6.4% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-007 KAT-Coder-Pro V1 Terminal-Bench Hard Overall 9.1% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-008 KAT-Coder-Pro V1 Terminal-Bench 2.1 Overall 70% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-009 KAT-Coder-Pro V1 CritPt Overall 0% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-010 KAT-Coder-Pro V1 AA-Omniscience Overall -37.4 Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-011 KAT-Coder-Pro V1 AA-Omniscience Accuracy 17.5% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-012 KAT-Coder-Pro V1 IFBench Overall 68.4% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-013 KAT-Coder-Pro V1 GDPval-AA Average Normalized Score 19.8% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV1-014 KAT-Coder-Pro V1 AA-LCR Overall 74% Unknown Primary source KWAI-KATCODERPROV1
BR-040KATCODERPROV2-001 KAT Coder Pro V2 Artificial Analysis Intelligence Index Overall 35.4 Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-002 KAT Coder Pro V2 GPQA Diamond Accuracy 85.5% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-003 KAT Coder Pro V2 Humanity's Last Exam No tools Overall 16% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-004 KAT Coder Pro V2 SciCode Overall 38.3% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-005 KAT Coder Pro V2 tau2-bench Overall 89.5% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-006 KAT Coder Pro V2 tau3-Banking Overall 5.8% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-007 KAT Coder Pro V2 Terminal-Bench Hard Overall 49.2% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-008 KAT Coder Pro V2 CritPt Overall 0% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-009 KAT Coder Pro V2 AA-Omniscience Overall -21.6 Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-010 KAT Coder Pro V2 AA-Omniscience Accuracy 22% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-011 KAT Coder Pro V2 IFBench Overall 66.7% Unknown Primary source KWAI-KATCODERPROV2
BR-040KATCODERPROV2-012 KAT Coder Pro V2 AA-LCR Overall 66% Unknown Primary source KWAI-KATCODERPROV2