{"slug": "benchpress-predict-any-llm-s-score-on-any-benchmark", "title": "BenchPress: Predict any LLM's score on any benchmark", "summary": "A new tool called BenchPress allows users to predict any large language model's score on any benchmark, using a score matrix derived from reported evaluations. The project invites community contributions to expand its predictive capabilities.", "body_md": "Predict any LLM's score on any benchmark.\n\n01 / 02\n\nScore\n\nLeaderboard\n\nResources\n\nUse the code to reproduce the paper, or download the score matrix behind the predictor.\n\nContribute\n\nReport benchmark scores for a model. Include the model, benchmark, score, evaluation setting, effort, and source; we will review provenance before adding it to the matrix.", "url": "https://wpnews.pro/news/benchpress-predict-any-llm-s-score-on-any-benchmark", "canonical_source": "https://microsoft.github.io/benchpress/", "published_at": "2026-06-24 03:22:59+00:00", "updated_at": "2026-06-24 03:44:30.160580+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-research"], "entities": ["BenchPress"], "alternates": {"html": "https://wpnews.pro/news/benchpress-predict-any-llm-s-score-on-any-benchmark", "markdown": "https://wpnews.pro/news/benchpress-predict-any-llm-s-score-on-any-benchmark.md", "text": "https://wpnews.pro/news/benchpress-predict-any-llm-s-score-on-any-benchmark.txt", "jsonld": "https://wpnews.pro/news/benchpress-predict-any-llm-s-score-on-any-benchmark.jsonld"}}