Simply passing unit tests (like in SWE-bench) is a weak signal of a coding AI's usefulness. A far better evaluation is whether a senior engineer would actually merge its solution into the main codebase. This holistic judgment accounts for code patterns, test quality, and architectural consistency, which current benchmarks miss.

Traditional AI coding benchmarks are gamed or saturated. A new benchmark, DeepSWE, uses novel, complex tasks, revealing a massive performance gap where models like GPT-5.5 excel at 70%, while others trail by over 30 percentage points, contrary to other benchmarks that show them as close competitors.

A benchmark like SWE-Bench is valuable when models score 20%, but becomes meaningless noise once models achieve 80%+ scores. At that point, improvements reflect guessing arbitrary details (like function names) rather than genuine capability. This demonstrates that benchmarks have a natural lifecycle and must be retired once saturated to avoid misleading progress metrics.

OpenAI's evals team is looking beyond current benchmarks that test self-contained, hour-long tasks. They are calling for new evaluations that measure performance on problems that would take top engineers weeks or months to solve, such as creating entire products end-to-end. This signals a major increase in the complexity and ambition expected from future AI benchmarks.

As benchmarks become standard, AI labs optimize models to excel at them, leading to score inflation without necessarily improving generalized intelligence. The solution isn't a single perfect test, but continuously creating new evals that measure capabilities relevant to real-world user needs.

Just as standardized tests fail to capture a student's full potential, AI benchmarks often don't reflect real-world performance. The true value comes from the 'last mile' ingenuity of productization and workflow integration, not just raw model scores, which can be misleading.

Early benchmark improvements focused on adding more languages and repositories. Now, the cutting edge involves creating more difficult evaluation splits through sophisticated curation techniques. Researchers must justify why their new benchmark is qualitatively harder, not just broader, than existing ones.

Traditional AI benchmarks are seen as increasingly incremental and less interesting. The new frontier for evaluating a model's true capability lies in applied, complex tasks that mimic real-world interaction, such as building in Minecraft (MC Bench) or managing a simulated business (VendingBench), which are more revealing of raw intelligence.

The rapid improvement of AI models is maxing out industry-standard benchmarks for tasks like software engineering. To truly understand AI's impact and capability, companies must develop their own evaluation systems tailored to their specific workflows, rather than waiting for external studies.