Evals and quality radar
Where are frontier labs exposing eval, benchmark, quality, red-team, observability, or model behavior testing demand? Matches are deterministic keyword/lane classifications over frontier-lab public signals.
Matched termsevalevalsevaluationbenchmarkbenchmarksqualitymeasurementobservabilityred teamtesting
Matched signal ledger
json →TimeOrgKindSignalScore
1wTencent HunyuanRepoTencent-Hunyuan/DiagSafeTencent Hunyuan has a repo signal matching data demand, evals and quality, safety and policy.labelbenchmarksafetyradar 38Sep 18NVIDIARepoNVIDIA/swe-serveNVIDIA has a repo signal matching evals and quality, infrastructure, product and customer.benchmarkinferenceproductradar 384wMicrosoftRepomicrosoft/agent365-runbookMicrosoft has a repo signal matching data demand, evals and quality.dataobservabilityradar 261dAnthropicWritingStrategic Warning For Ai Risk Progress And Insights From Our Frontier Red TeamAnthropic has a writing signal matching evals and quality, safety and policy.red teamriskradar 252wNVIDIAModelnvidia/Nemotron-3.5-Embed-8B-BF16NVIDIA has a model signal matching data demand, evals and quality.retrievalevalradar 252wNVIDIAModelnvidia/Nemotron-3.5-Embed-1B-BF16NVIDIA has a model signal matching data demand, evals and quality.retrievalevalradar 25Sep 4Tencent HunyuanModeltencent/EVIE-8BTencent Hunyuan has a model signal matching data demand, evals and quality.retrievalevalradar 25Sep 4Tencent HunyuanModeltencent/EVIE-4.5BTencent Hunyuan has a model signal matching data demand, evals and quality.retrievalevalradar 25Oct 4AnthropicWritingEvaluating Ai SystemsAnthropic has a writing signal matching evals and quality, infrastructure.evalsystemsradar 25Aug 22AnthropicWritingRed Teaming Language Models To Reduce Harms Methods Scaling Behaviors And Lessons LearnedAnthropic has a writing signal matching evals and quality, infrastructure.red teamscalingradar 255dOpenAIRepoopenai/MultiLangBenchOpenAI has a repo signal matching evals and quality.evalbenchmarkbenchmarksradar 181wTencent HunyuanRepoTencent-Hunyuan/OmniCapBenchTencent Hunyuan has a repo signal matching evals and quality.evalevaluationradar 16May 22AnthropicWritingExploit EvalsAnthropic has a writing signal matching evals and quality.evalevalsradar 151wAmazon (Nova)Repoamazon-science/ListQA-EvalAmazon (Nova) has a repo signal matching evals and quality.evalradar 144wAmazon (Nova)Repoamazon-science/SynthAVEAmazon (Nova) has a repo signal matching evals and quality.benchmarkradar 14May 1NVIDIAForkNVIDIA/cell-evalNVIDIA has a fork signal matching evals and quality.evalradar 14Jan 26AnthropicForkanthropics/nix-eval-jobsAnthropic has a fork signal matching evals and quality.evalradar 14Oct 25AnthropicWritingEvaluating Feature SteeringAnthropic has a writing signal matching evals and quality.evalradar 14May 31CohereForkcohere-ai/terraform-oci-cis-landing-zone-observabilityCohere has a fork signal matching evals and quality.observabilityradar 144wMicrosoftModelmicrosoft/rho-roboevalMicrosoft has a model signal matching evals and quality.evalradar 13Jan 14AnthropicWritingProperty Based TestingAnthropic has a writing signal matching evals and quality.testingradar 13Dec 7AnthropicWritingEvaluating And Mitigating Discrimination In Language Model DecisionsAnthropic has a writing signal matching evals and quality.evalradar 13