BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

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

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

Moonshot AI

Provider prefix
KIMI
Benchmark Record namespace
010

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-010K27CODE-001 Kimi K2.7-code DeepSWE Resolved 31% ±1% Unknown Primary source KIMI-K27CODE
BR-010KIMIK2-001 Kimi K2 Artificial Analysis Intelligence Index Overall 19.4 Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-002 Kimi K2 GPQA Diamond Accuracy 76.6% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-003 Kimi K2 Humanity's Last Exam No tools Overall 7% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-004 Kimi K2 SciCode Overall 34.5% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-005 Kimi K2 tau2-bench Overall 61.1% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-006 Kimi K2 Terminal-Bench Hard Overall 15.9% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-007 Kimi K2 CritPt Overall 0% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-008 Kimi K2 AA-Omniscience Overall -27.5 Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-009 Kimi K2 AA-Omniscience Accuracy 26.8% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-010 Kimi K2 IFBench Overall 41.5% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-011 Kimi K2 AA-LCR Overall 51% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK2-012 Kimi K2 SWE-bench Pro Public Dataset Resolved 27.67 ±3.25 Unknown Primary source KIMI-KIMIK2
BR-010KIMIK20905-001 Kimi K2 0905 Artificial Analysis Intelligence Index Overall 23.5 Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-002 Kimi K2 0905 GPQA Diamond Accuracy 76.7% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-003 Kimi K2 0905 Humanity's Last Exam No tools Overall 6.3% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-004 Kimi K2 0905 SciCode Overall 30.7% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-005 Kimi K2 0905 tau2-bench Overall 73.4% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-006 Kimi K2 0905 Terminal-Bench Hard Overall 23.5% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-007 Kimi K2 0905 CritPt Overall 0% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-008 Kimi K2 0905 AA-Omniscience Overall -26.5 Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-009 Kimi K2 0905 AA-Omniscience Accuracy 25.4% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-010 Kimi K2 0905 IFBench Overall 41.7% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK20905-011 Kimi K2 0905 AA-LCR Overall 52.3% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK25-001 Kimi K2.5 Artificial Analysis Intelligence Index Overall 38.1 Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-002 Kimi K2.5 GPQA Diamond Accuracy 87.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-003 Kimi K2.5 Humanity's Last Exam No tools Overall 29.4% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-004 Kimi K2.5 SciCode Overall 49% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-005 Kimi K2.5 tau2-bench Overall 95.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-006 Kimi K2.5 Terminal-Bench Hard Overall 34.8% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-007 Kimi K2.5 CritPt Overall 3.1% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-008 Kimi K2.5 AA-Omniscience Overall -8.1 Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-009 Kimi K2.5 AA-Omniscience Accuracy 34.3% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-010 Kimi K2.5 IFBench Overall 70.2% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-011 Kimi K2.5 APEX-Agents Overall 11.5% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-012 Kimi K2.5 MMMU-Pro Overall 75.4% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-013 Kimi K2.5 AA-LCR Overall 65.3% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-014 Kimi K2.5 Artificial Analysis Intelligence Index Overall 29.4 Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-015 Kimi K2.5 GPQA Diamond Accuracy 78.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-016 Kimi K2.5 Humanity's Last Exam No tools Overall 12.3% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-017 Kimi K2.5 SciCode Overall 39.6% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-018 Kimi K2.5 tau2-bench Overall 81.3% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-019 Kimi K2.5 Terminal-Bench Hard Overall 18.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-020 Kimi K2.5 CritPt Overall 0.6% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-021 Kimi K2.5 AA-Omniscience Overall -14 Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-022 Kimi K2.5 AA-Omniscience Accuracy 22.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-023 Kimi K2.5 IFBench Overall 43.7% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-024 Kimi K2.5 MMMU-Pro Overall 73.1% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-025 Kimi K2.5 AA-LCR Overall 59% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-026 Kimi K2.5 ARC-AGI-1 Overall 65.3% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-027 Kimi K2.5 ARC-AGI-2 Overall 11.8% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK26-001 Kimi K2.6 Artificial Analysis Intelligence Index Overall 44.2 Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-002 Kimi K2.6 GPQA Diamond Accuracy 91.1% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-003 Kimi K2.6 Humanity's Last Exam No tools Overall 35.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-004 Kimi K2.6 SciCode Overall 53.5% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-005 Kimi K2.6 tau2-bench Overall 95.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-006 Kimi K2.6 tau3-Banking Overall 20.6% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-007 Kimi K2.6 Terminal-Bench Hard Overall 43.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-008 Kimi K2.6 Terminal-Bench 2.1 Overall 65.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-009 Kimi K2.6 CritPt Overall 8% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-010 Kimi K2.6 AA-Omniscience Overall 6.4 Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-011 Kimi K2.6 AA-Omniscience Accuracy 32.8% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-012 Kimi K2.6 IFBench Overall 76% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-013 Kimi K2.6 APEX-Agents Overall 28.5% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-014 Kimi K2.6 ITBench SRE Overall 31.2% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-015 Kimi K2.6 GDPval-AA Average Normalized Score 34.5% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-016 Kimi K2.6 MMMU-Pro Overall 79.4% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-017 Kimi K2.6 AA-LCR Overall 69.7% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-018 Kimi K2.6 Artificial Analysis Intelligence Index Overall 34.6 Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-019 Kimi K2.6 GPQA Diamond Accuracy 78.8% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-020 Kimi K2.6 Humanity's Last Exam No tools Overall 18.2% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-021 Kimi K2.6 SciCode Overall 39.5% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-022 Kimi K2.6 tau2-bench Overall 93.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-023 Kimi K2.6 Terminal-Bench Hard Overall 37.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-024 Kimi K2.6 CritPt Overall 1.4% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-025 Kimi K2.6 AA-Omniscience Overall -10 Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-026 Kimi K2.6 AA-Omniscience Accuracy 23.1% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-027 Kimi K2.6 IFBench Overall 44.3% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-028 Kimi K2.6 AA-LCR Overall 57.7% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK27CODE-001 Kimi K2.7 Code Artificial Analysis Intelligence Index Overall 41.9 Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-002 Kimi K2.7 Code GPQA Diamond Accuracy 89.6% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-003 Kimi K2.7 Code Humanity's Last Exam No tools Overall 32.8% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-004 Kimi K2.7 Code SciCode Overall 47.5% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-005 Kimi K2.7 Code tau2-bench Overall 90.1% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-006 Kimi K2.7 Code tau3-Banking Overall 18.1% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-007 Kimi K2.7 Code Terminal-Bench Hard Overall 44.7% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-008 Kimi K2.7 Code Terminal-Bench 2.1 Overall 67.4% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-009 Kimi K2.7 Code CritPt Overall 10% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-010 Kimi K2.7 Code AA-Omniscience Overall -10.7 Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-011 Kimi K2.7 Code AA-Omniscience Accuracy 38.6% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-012 Kimi K2.7 Code IFBench Overall 63.1% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-013 Kimi K2.7 Code GDPval-AA Average Normalized Score 34.3% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-014 Kimi K2.7 Code AA-LCR Overall 66.3% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK27CODE-015 Kimi K2.7 Code CursorBench 3.2 Overall 49.7% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK2THINKING-001 Kimi K2 Thinking Artificial Analysis Intelligence Index Overall 32.7 Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-002 Kimi K2 Thinking GPQA Diamond Accuracy 83.8% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-003 Kimi K2 Thinking Humanity's Last Exam No tools Overall 22.3% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-004 Kimi K2 Thinking SciCode Overall 42.4% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-005 Kimi K2 Thinking tau2-bench Overall 93% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-006 Kimi K2 Thinking Terminal-Bench Hard Overall 31.1% Unknown Primary source KIMI-KIMIK2THINKING