Havuz

Robot data infrastructure and runtime: turn video, state, actions, and telemetry into training episodes, RL environments, policy rollouts, a

从原作台词蒸馏角色的说话方式，落成可验证的 prompt 约束

Raw benchmark logs for Swift-Qwen3.8-27B vs the Qwen3.8-27B BF16 base: every response, score, and config across 9 benchmarks

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.

Project page for AV-Phys Bench: Do Joint Audio-Video Generation Models Understand Physics?

EvalPort — The Open LLM Evaluation Standard. Portable test cases, graders, suites, and results across DeepEval, Promptfoo, Inspect AI, and m

A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, reproducible experiment

Catches multilingual voice agents placing the wrong order. τ-bench style benchmark + CI gate for voice ordering agents in English and Hingli

Research prototype for trace-based observability and failure analysis in retrieval-augmented generation.

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.