SOURCE-LINKED INTELLIGENCE

API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and sycophancy. We find systematic API--interface differences in both accuracy and consistency. On average, API evaluations score 3.4 percentage points highe

Read original source ↗ Open in workspace

recordType

paper

region

Global