BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Tencent

Provider prefix
TCNT
Benchmark Record namespace
035

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-035HY3PREVIEW-001 Hy3-preview Artificial Analysis Intelligence Index Overall 33.6 Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-002 Hy3-preview GPQA Diamond Accuracy 86.7% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-003 Hy3-preview Humanity's Last Exam No tools Overall 25.5% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-004 Hy3-preview SciCode Overall 41.2% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-005 Hy3-preview tau2-bench Overall 92.7% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-006 Hy3-preview Terminal-Bench Hard Overall 34.1% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-007 Hy3-preview CritPt Overall 4.6% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-008 Hy3-preview AA-Omniscience Overall -34.6 Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-009 Hy3-preview AA-Omniscience Accuracy 28% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-010 Hy3-preview IFBench Overall 63.1% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-011 Hy3-preview AA-LCR Overall 54.7% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-012 Hy3-preview Artificial Analysis Intelligence Index Overall 26.1 Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-013 Hy3-preview GPQA Diamond Accuracy 73.2% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-014 Hy3-preview Humanity's Last Exam No tools Overall 6.3% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-015 Hy3-preview SciCode Overall 39.4% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-016 Hy3-preview tau2-bench Overall 67.5% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-017 Hy3-preview Terminal-Bench Hard Overall 31.8% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-018 Hy3-preview CritPt Overall 0.3% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-019 Hy3-preview AA-Omniscience Overall -36.4 Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-020 Hy3-preview AA-Omniscience Accuracy 22.4% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-021 Hy3-preview IFBench Overall 48% Unknown Primary source TCNT-HY3PREVIEW
BR-035HY3PREVIEW-022 Hy3-preview AA-LCR Overall 33.7% Unknown Primary source TCNT-HY3PREVIEW