specific method · filed under evaluation
Living in-house benchmark suite
An in-house benchmark suite that is frequently refreshed and expanded to track evolving model failures and guide training iterations.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
These benchmarks are refreshed and expanded frequently, so that they can closely track the model’s evolving failure modes and directly guide data and training iterations.
coreevaluation onlyin Kimi K3 in-house benchmark suiteMoonshot AI
Filed alongside
Other methods under evaluation :: benchmark.
High-confidence ProgramBench subsetArtificial Analysis Intelligence IndexBrowseComp with SearchCAD visual reproductionCapture-the-Flag (CTF) evaluationComputer use closed-loop evaluationDisabling tool searchDomain whitelistExecution-grounded evaluationF2P/P2F acceptance criterionFail-to-pass and pass-to-pass evaluation pointsGPU kernel optimization task suiteKernelBenchLongBench v2Multiple-rollout evaluationPaperBenchPinchBenchProfBench with SearchScaleAI Multi Challenge Multi Turn Instruction FollowingSQuADSWE-bench VerifiedThree-configuration cyber range testingVals.aiVerified CUDA kernels