Nexa-gauge

v0.1.16 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 10d AI Coding Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

blue-score geval grounding llm llm-eval llm-evaluation-framework

+5 more

llm-judge ranking-algorithm redteam relevance-scoring rouge-metric

ReleasePort's take

Light signal

editorial:auto 10d

GEval v0.1.16 introduces likert and binary scoring modes with optional reasoning.

Why it matters: The new GEval scoring modes enable more flexible evaluation setups, supporting both quantitative (likert) and definitive (binary) assessments while allowing inclusion of explanatory reasoning for each score.

Summary

AI summary

GEval adds likert and binary scoring modes with optional reasoning

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Adds GEval scoring modes likert and binary with optional reasoning. Adds GEval scoring modes likert and binary with optional reasoning. Source: llm_adapter@2026-05-24 Confidence: high	—

Full changelog

0.1.16 (2026-05-24)

Features

GEval scoring modes (likert/binary) and optional reasoning (#57) (5435308)

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Nexa-gauge

Get notified when new releases ship.

About Nexa-gauge

All releases →