{"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=Llama-3.1-8B&bench=MMLU","json_url":"https://assignee.net/benchmarks/evidence.json?model=Llama-3.1-8B&bench=MMLU","model":"Llama-3.1-8B","benchmark":"MMLU","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":2025,"year_max":2026,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":44.9,"max_score_pct":78.2},"spread_pp":33.3,"severity":"HIGH","entries":[{"model":"Llama-3.1-8B","benchmark":"MMLU","score_pct":78.2,"source_title":"Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report","source_url":"http://arxiv.org/abs/2601.21051v1","source_domain":"arxiv.org","year":2026},{"model":"Llama-3.1-8B","benchmark":"MMLU","score_pct":66.9,"source_title":"Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark","source_url":"http://arxiv.org/abs/2503.20786v1","source_domain":"arxiv.org","year":2025},{"model":"Llama-3.1-8B","benchmark":"MMLU","score_pct":63.5,"source_title":"Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct","source_url":"http://arxiv.org/abs/2601.14277v1","source_domain":"arxiv.org","year":2026},{"model":"Llama-3.1-8B","benchmark":"MMLU","score_pct":44.88,"source_title":"Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment","source_url":"http://arxiv.org/abs/2602.21346v1","source_domain":"arxiv.org","year":2026}],"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."]}