Are Benchmarks Reliable? Toward Structural Diagnosis via Item-Level Capability Boundaries

arXiv:2609.33196 · cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.AI

Submitted: 2026-09-27

Updated: 2026-10-12

Comments: Submitted to NeurIPS 2026; Rejected with reviewer scores of 4,4,4

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 121× in this paper · explained in 2 episodes
• Consistency — 23× in this paper · explained in 3 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Self-consistency — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• External Validation — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• Normalized Discrimination Ratio — 1× in this paper
• Quantifying Uncertainty — 1× in this paper · explained in 5 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Training Verifiers to Solve Math Word Problems
• AI Evaluation Should Require Standardized Item-Level Data Releases
• Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores
• Scaling Laws for Neural Language Models
• Position: AI Evaluations Should be Grounded on a Theory of Capability
• Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems