DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV
Tool radar
p

Evaluation · Documentation review

promptfoo

Versioned prompt and model evaluations that can run in CI.

promptfoo compares prompts, providers and application outputs against configured tests. It supports deterministic assertions, model-based grading and security testing, with CLI and library workflows. The command documentation describes failure exit codes so quality gates can be connected to CI rather than reviewed only in screenshots.

Official documentationReviewed 23 Sept 2026
Source-checked Sources & corrections

A good fit for

  • → Prompt regression tests
  • → Side-by-side provider comparisons
  • → Authorized application red teaming

Know the limits

  • → Generated tests can repeat the assumptions of the model that wrote them.
  • → Judge-based assertions can be noisy or biased.
  • → Security testing needs explicit authorization and safe test data.

Your first useful workflow

01

Specify failures

Write test cases from real product requirements and previous incidents.

02

Choose assertions

Prefer deterministic checks for structure and policy boundaries; calibrate subjective judges.

03

Wire the gate

Verify that a failed test actually fails CI and that artifacts are saved.

The practical take

An eval suite earns trust by catching regressions you care about, not by producing a green percentage.

Sources & evidence

Capabilities above are summarized from these official documents. Workflow suggestions are editorial guidance, not a claim of measured product superiority.