{"schema":"https://assignee.net/schemas/benchmark-evidence-v1","schema_version":"1.0","contract_version":"benchmark-evidence-v1.0","contract_updated":"2026-06-01","schema_documentation":"https://assignee.net/schemas","changelog_url":"https://assignee.net/changelog","publisher":{"name":"Assignee Research","url":"https://assignee.net"},"html_url":"https://assignee.net/benchmarks/evidence?model=GPT-4o&bench=HumanEval","json_url":"https://assignee.net/benchmarks/evidence.json?model=GPT-4o&bench=HumanEval","model":"GPT-4o","benchmark":"HumanEval","source_count":4,"source_coverage":{"record_count":4,"distinct_source_count":4,"coverage_level":"MODERATE","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":4,"missing_source_url_count":0,"domains":["arxiv.org"],"year_min":2024,"year_max":2025,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":3.4,"max_score_pct":86.2},"spread_pp":82.8,"severity":"HIGH","entries":[{"model":"GPT-4o","benchmark":"HumanEval","score_pct":86.2,"source_title":"FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks","source_url":"https://arxiv.org/abs/2504.06939","source_domain":"arxiv.org","year":2025},{"model":"GPT-4o","benchmark":"HumanEval","score_pct":86.2,"source_title":"FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks","source_url":"http://arxiv.org/abs/2504.06939v2","source_domain":"arxiv.org","year":2025},{"model":"GPT-4o","benchmark":"HumanEval","score_pct":27.7,"source_title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","source_url":"http://arxiv.org/abs/2410.12381v3","source_domain":"arxiv.org","year":2024},{"model":"GPT-4o","benchmark":"HumanEval","score_pct":3.42,"source_title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","source_url":"http://arxiv.org/abs/2501.01054v1","source_domain":"arxiv.org","year":2025}],"interpretation":"This record groups score claims extracted from papers for the same model and benchmark label. A nonzero spread means the public literature reports different values for this cluster.","limitations":["Differences are not automatically errors.","Reported values may differ because of prompts, dataset versions, evaluation protocols, scoring rules, preprocessing, fine-tuning, or reporting conventions.","Source papers remain authoritative for their own claims."]}