News Tag
model evaluation
The latest Data Phoenix news tagged model evaluation.
Latest
NewsAllen Institute for AI releases StateBench for long-document state tracking
NewsAi2 releases XYBench to test how assistants handle mistaken premises
NewsApple study finds MMLU weakly tracks LLM judge quality
NewsOpenAI introduces LifeVal benchmark for everyday AI tasks
NewsProperty Finder rebuilds AI benchmark, reports 86% lower inference cost
NewsCoding-agent harnesses can triple costs without clear accuracy gains, study finds
NewsAnthropic pitches lawmakers on draft frontier AI safety bill
NewsAnthropic opens Singapore office and signs government AI MOU
NewsApple study finds LLM translation grading unreliable in most settings
NewsCoreWeave launches Forge to link the production AI workflow
NewsTII launches Falcon-Emirati-7B for Emirati Arabic
NewsApple study finds LLM conditioning gains can reduce fluency