|
EVALution — AI evaluation for teams shipping LLM features
EVALution helps companies integrating AI measure whether it actually works: evaluation frameworks, pre-launch readiness audits, and regression evals that run...
|
80 % |
|
Evals AI - Thoughtful AI evaluations for modern teams
A calmer, more deliberate workspace for prompt testing, model evaluation, and AI product decisions.
|
80 % |
|
EvaliQA, the AI Evaluation and AI Testing Platform
Test and monitor AI systems without a line of code, with generated test cases, AI judges, RAG and AI agent metrics, red teaming and voice evals.
|
80 % |
|
GQODB
GQODB — point-in-time market data storage. Open codec (tick and order book, at any depth), commercial engine: raw journal, ledger, receipts, recovery and cau...
|
80 % |
|
InnoWaveTec – Notes on engineering, markets, and quantitative research
|
79 % |
|
Repath — Progressive Delivery for AI
Canary rollouts for prompts and models: real traffic, judged quality, automatic rollback.
|
79 % |
|
GAMATIQ — Know which decisions your models get wrong, before you act on them
GAMATIQ scores the reliability of every prediction your underwriting, fraud, and quality-control models make, so your team reviews the few decisions that mat...
|
79 % |
|
Evaluator Integrity
Your AI system can pass its evaluator and still be wrong. Evaluator Integrity tests the LLM judges and evaluation pipelines AI teams rely on, before their sc...
|
79 % |
|
瑞通 Ruitong — Cross-Accelerator Equivalence Reference
Reference accuracy deltas for the same LLM across different accelerators. Open method, reproducible, vendor-neutral.
|
79 % |
|
jeval — Know when your AI gets it wrong.
Open-source evaluations for AI outputs and agents. Define your checks, run them with Jev, and inspect failures and uncertain results.
|
79 % |
|
Score Your Pass — Co.De Triage
An honest pass-quality forecast for the SatNOGS community — the real model runs in your browser.
|
78 % |
|
CIMO Labs | Causal Evaluation for LLM Systems
Open research effort to formalize causal inference methods for evaluating generative models. Calibrate cheap metrics to expensive labels, apply at scale, det...
|
78 % |
|
Kengly · A forecasting system that keeps its own score
Every night Kengly reads posts on X, news articles and market data, turns them into dated, falsifiable claims, and grades them once the deadline passes. The...
|
78 % |
|
Polymet Films | The half of the equation you have never been able to see
Reliability is roughly 80 percent process and 20 percent raw material. Polymet Films shares lot level raw material and metallising data so your engineering t...
|
78 % |
|
Ophanim — the AI shows its work
An AI day-trading desk for 0DTE SPY that shows its evidence — calibrated scores, plain-English reasons, honest records. You decide.
|
78 % |
|
Invariant Markets
Invariant Markets brings market structure, positioning, macro context, and evidence-led research into one analytical workspace.
|
78 % |
|
Ares Intelligent Systems
Ares Intelligent Systems builds scientific systems that mark the parts of an answer they cannot support.
|
78 % |
|
Lana Rafaella
Lana Rafaella - AI Evaluation Engineer and Senior QA Engineer. Evaluation harnesses, golden baselines and release gates for AI and payment systems.
|
78 % |
|
Clearwood, reliability monitoring for enterprise AI agents
Clearwood reads model intent to catch failures that slip past your monitors and pass review, at a fraction of the cost of an always-on LLM judge.
|
78 % |
|
TokenRoute | Evidence-backed model routing
TokenRoute benchmarks real prompts across local, private, and BYOK cloud models, scores the evidence, and exports route decisions your apps can use.
|
78 % |
Detected social media networks