Exact model identity

Kimi K2.6

Moonshot AI · version status: reported

Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID kimi-k2-6.

Evaluation settings

Numeric results

BenchmarkWorkRun / groupMetricValue
GeneBench-ProGeneBench-Pro: Evaluating Multistage Statistical Reasoning in Genomics, Quantitative Biology, and Translational Biomedicinegenebench-pro-official
genebench-pro-paper-v1-full-standard-xhigh
Eval-level pass rate4.4 percent