Traditional, static benchmarks for AI models go stale almost immediately. The superior approach is creating dynamic benchmarks that update constantly based on real-world usage and user preferences, which can then be turned into products themselves, like an auto-routing API.
Related Insights
Static benchmarks are easily gamed. Dynamic environments like the game Diplomacy force models to negotiate, strategize, and even lie, offering a richer, more realistic evaluation of their capabilities beyond pure performance metrics like reasoning or coding.
Public leaderboards like LM Arena are becoming unreliable proxies for model performance. Teams implicitly or explicitly "benchmark" by optimizing for specific test sets. The superior strategy is to focus on internal, proprietary evaluation metrics and use public benchmarks only as a final, confirmatory check, not as a primary development target.
Standardized benchmarks for AI models are largely irrelevant for business applications. Companies need to create their own evaluation systems tailored to their specific industry, workflows, and use cases to accurately assess which new model provides a tangible benefit and ROI.
Don't trust academic benchmarks. Labs often "hill climb" or game them for marketing purposes, which doesn't translate to real-world capability. Furthermore, many of these benchmarks contain incorrect answers and messy data, making them an unreliable measure of true AI advancement.
The primary bottleneck in improving AI is no longer data or compute, but the creation of 'evals'—tests that measure a model's capabilities. These evals act as product requirement documents (PRDs) for researchers, defining what success looks like and guiding the training process.
While AI labs tout performance on standardized tests like math olympiads, these metrics often don't correlate with real-world usefulness or qualitative user experience. Users may prefer a model like Anthropic's Claude for its conversational style, a factor not measured by benchmarks.
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.
As foundational AI models become commoditized, the key differentiator is shifting from marginal improvements in model capability to superior user experience and productization. Companies that focus on polish, ease of use, and thoughtful integration will win, making product managers the new heroes of the AI race.
An analysis of AI model performance shows a 2-2.5x improvement in intelligence scores across all major players within the last year. This rapid advancement is leading to near-perfect scores on existing benchmarks, indicating a need for new, more challenging tests to measure future progress.
Standardized AI benchmarks are saturated and becoming less relevant for real-world use cases. The true measure of a model's improvement is now found in custom, internal evaluations (evals) created by application-layer companies. Progress for a legal AI tool, for example, is a more meaningful indicator than a generic test score.
