Benchmarks / Kai / Joint decisions
Kai · CapabilityJoint decisions
Several typed fields decided together on one case, scored on all of them at once.
Latest
History
One result so far. Its history fills in as later runs are posted.
| Measured | Subject | Metric | Value | Baseline | Result | Status |
|---|---|---|---|---|---|---|
| Sep 28, 2026 | Kai a6 · a211cc70 | Accuracy | 30.6% | Jev 83.7% | Loss | Live · Hanzo-measured |
Conditions
the same cases to both modelsJev: typesafe/jev-1.13, measured Sep 27, 2026Hardware
on dgx
Source
research run cap.joint-cases-a6.a211cc70-kai
Reproduce
bench cap --harness . --who kai,jev --kai <checkpoint> # in hanzoai/benchmarks/decision
More Kai benchmarks
AG News · DAIR Emotion · Banking77 · Support triage · Email spam · Phishing · Jailbreak · Toxicity · RAG relevance · Model routing · Typed decisions · MASSIVE · AG News, validation split · Support triage, validation split · Typed decisions, validation split · HarmBench (benign prompts) · Choosing among many options · Release gate against Jev · Latency of one decision
Every result for Joint decisions on the shelf · How these are measured