# Typed decisions benchmark · Kai — Hanzo AI

> Kai and Jev on the same 2,000 questions of Typed decisions, one run per Kai revision.

[Benchmarks](https://hanzo.ai/benchmarks) / [Kai](https://hanzo.ai/benchmarks?product=Kai#all) / Typed decisions

Kai · Decision harness

# Typed decisions

Kai and Jev on the same 2,000 questions of Typed decisions, one run per Kai revision.

## Latest

[74.6%Accuracy · kai-1.4 · c1856a77Jev 73.6% · Win · Oct 16, 2026 · Hanzo-measured](#history)

## History

5 results, newest first. Superseded runs stay, so a revision's progress can be read.

Measured

Subject

Metric

Value

Baseline

Result

Status

Oct 16, 2026

kai-1.4 · c1856a77

Accuracy

74.6%

Jev 73.6%

Win

Live · Hanzo-measured

Oct 3, 2026

kai-1 · 0834a74f

Accuracy

75.9%

Jev 73.6%

Win

Superseded · Hanzo-measured

Sep 28, 2026

Kai a8 · 0cfeef05

Accuracy

76.1%

Jev 73.6%

Win

Superseded · Hanzo-measured

Sep 28, 2026

Kai a7 · 0834a74f

Accuracy

75.9%

Jev 73.6%

Win

Superseded · Hanzo-measured

Sep 28, 2026

Kai a6 · a211cc70

Accuracy

75.0%

Jev 73.6%

Win

Superseded · Hanzo-measured

## Conditions

split: harness2,000 questions, 2,000 answereddataset dde140a63fc56 Kai revisions measuredJev: typesafe/jev-1.13-20260917, measured Sep 25, 2026

## Hardware

CPU AS SERVED

## Source

[research run typed_decisions-harness-kai-1.4.c1856a77-kai](https://api.hanzo.ai/v1/research/runs?org=hanzo&id=typed_decisions-harness-kai-1.4.c1856a77-kai)

## Reproduce

`bench score --harness . --kai results/kai/preds.json.gz --out results/scores.json # in hanzoai/benchmarks/decision @ 5f616dd`

## More Kai benchmarks

[AG News](https://hanzo.ai/benchmarks/kai-ag-news) · [DAIR Emotion](https://hanzo.ai/benchmarks/kai-dair-emotion) · [Banking77](https://hanzo.ai/benchmarks/kai-banking77) · [Support triage](https://hanzo.ai/benchmarks/kai-support-triage) · [Email spam](https://hanzo.ai/benchmarks/kai-email-spam) · [Phishing](https://hanzo.ai/benchmarks/kai-phishing) · [Toxicity](https://hanzo.ai/benchmarks/kai-toxicity) · [RAG relevance](https://hanzo.ai/benchmarks/kai-rag-relevance) · [Model routing](https://hanzo.ai/benchmarks/kai-model-routing) · [MASSIVE](https://hanzo.ai/benchmarks/kai-massive) · [Choosing among many options](https://hanzo.ai/benchmarks/kai-choice-size) · [Latency of one decision](https://hanzo.ai/benchmarks/kai-latency)

[Every result for Typed decisions on the shelf](https://hanzo.ai/benchmarks?q=Typed%20decisions#all) · [How these are measured](https://hanzo.ai/benchmarks#methods)