Reported Scores
| Model | Score | Source paper | Year |
|---|---|---|---|
| GPT-4 | 87.3% | Adaptive Self-Prompting in Agentic LLM Frameworks for Code Fault Detection / doi.org | 2026 |
| GPT-4 | 87.3% | Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs / arxiv.org | 2025 |
| GPT-4 | 87.3% | MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark / arxiv.org | 2024 |
| GPT-4 | 87.3% | Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities / doi.org | 2023 |
| GPT-4 | 87.3% | Capabilities of GPT-4 on Medical Challenge Problems / arxiv.org | 2023 |
| GPT-4 | 86.4% | Data Engineering for Scaling Language Models to 128K Context / arxiv.org | 2024 |
| GPT-4 | 57.0% | Investigating Data Contamination in Modern Benchmarks for Large Language Models / doi.org | 2023 |
Interpretation
This page 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.
Differences are not automatically errors. They may come from prompt choices, dataset versions, evaluation protocol, scoring rule, preprocessing, fine-tuning, or reporting convention. Source papers remain authoritative for their own claims. See the quality guide for how to read evidence links, manifests, and automated assessment fields.
Source coverage is a conservative count of distinct public paper URLs or titles in the cluster. It measures coverage breadth, not correctness.
Source profile reports public URL domains and publication years when they are available in extracted records. It is included for auditability only.