0288GitHub
JevBench
Benchmark for typed decision models across several suites, with confidence cascades and committees reported separately.
fstandhartinger/jevbenchREADME ↗
# JevBench — Benchmark for AI Decision Models [](https://github.com/fstandhartinger/jevbench/actions/workflows/tests.yml) Jev is TypeSafe AI's decision model; JevBench also evaluates Jev-compatible systems. The canonical JevBench board is https://benchmarkheaven.com/jev-models. ## Current results and scoring JevBench by Benchmark Heaven is a benchmark for AI decision models, including Jev-compatible systems. It measures typed decision accuracy, probability calibration, latency and cost. Maintained by Benchmark Heaven, independently of TypeSafe AI. [Current open-weights board](https://benchmarkheaven.com/jev-models) · [Hosted API board](https://benchmarkheaven.com/jev-models/api) · [Methodology](https://benchmarkheaven.com/jev-models/methodology) · [Data card](https://benchmarkheaven.com/jev-models/data) · [Benchmark comparison](https://benchmarkheaven.com/decision-model-benchmarks) Published release: **v1.6.1**, initially published 2026-10-06. [Version permalink](https://benchmarkheaven.com/jev-models/v1.6.1). Published addenda: a6 (2026-10-07), a7 (2026-10-07), a8 (2026-10-07), a11 (2026-10-08), a12 (2026-10-08); amended through 2026-10-08. Latest row measurement: 2026-10-07. This list includes additions embedded in the results artifact; method amendments and board revisions are listed separately on the versioned board. Cite source_sha256 5cd8c1332226ea9c179883d2285c0d8b8cc593ae38f2645197364a7ddd9c83c1 for the exact published bytes. The live board may also include later dated API reruns and presentation revisions. **Capability Score:** Arithmetic mean of Intelligence and Calibration; ranked models within both official caps. Headline on the open-weights board. Cost cap: USD 0.0646 per 1,000 decisions; adjusted median-latency cap: 1.23 seconds. **Composite Score: