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-010KIMIK2THINKING-010 Kimi K2 Thinking IFBench Overall 68.1% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMIK2THINKING-011 Kimi K2 Thinking AA-LCR Overall 66.3% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMILINEAR48BA3BINSTRUCT-001 Kimi Linear 48B A3B Instruct Artificial Analysis Intelligence Index Overall 8.5 Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-002 Kimi Linear 48B A3B Instruct GPQA Diamond Accuracy 41.2% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-003 Kimi Linear 48B A3B Instruct Humanity's Last Exam No tools Overall 2.7% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-004 Kimi Linear 48B A3B Instruct SciCode Overall 19.9% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-005 Kimi Linear 48B A3B Instruct tau2-bench Overall 0% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-006 Kimi Linear 48B A3B Instruct Terminal-Bench Hard Overall 11.4% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-007 Kimi Linear 48B A3B Instruct IFBench Overall 28.1% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-010KIMILINEAR48BA3BINSTRUCT-008 Kimi Linear 48B A3B Instruct AA-LCR Overall 25.7% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT