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

[ LAB — LIVE · no model calls ]

Eval Result Analyzer

Paste already-scored JSON records and calculate attempts, accepted outcomes, average latency, total cost and cost per accepted result for each candidate. Failed attempts remain in the bill. The sample uses fictional Candidate A and Candidate B labels and is explicitly illustrative.

All lab tools

Interactive workbench / no model calls

Default data is illustrative—not a real model benchmark.

Inputs are sent to this application's server for deterministic calculation and are not stored. Do not paste secrets or raw customer content.

How to use it

  1. 01

    Use records with candidate, passed, costUsd and latencyMs. Each row is one evaluated attempt.

  2. 02

    The analyzer validates types and non-negative values, groups records by candidate and computes the metrics.

  3. 03

    Export the summary. Keep your rubric, fixture version and traces alongside it; the analyzer cannot establish whether labels are correct.

Sources and methodology