Benchmarking became easy
Summary
The author created Any-Bench, a tool to benchmark AI models on personal codebases, addressing shortcomings in existing benchmarks like SWE-Bench.
Similar Articles
@Lyubh22: Coding benchmarks are saturating. AI4Research is the next frontier. Thrilled to see our MLS-Bench (https://mls-bench.co…
Announcing MLS-Bench, the first AI4Research benchmark to gain broad community adoption, testing AI agents on 140 executable tasks across 12 domains to propose modular ML improvements. The post includes leaderboard scores for models like Claude Opus 4.6 and GPT-5.4.
ProgramBench (5 minute read)
ProgramBench is a new benchmark that evaluates AI agents' ability to reconstruct complete software projects from compiled binaries and documentation without access to source code or decompilation tools.
New bench designed for smaller models: ObviousBench.com
ObviousBench is a new benchmark designed specifically for evaluating smaller AI models.
Introducing BenchBench (5 minute read)
Introduces BenchBench, a benchmark that tests AI models' ability to create effective benchmarks for other models, with GPT 5.2 being the only successful winner so far while frontier models like GPT 5.5 and Opus 4.6 struggled.
Benchmark Everything Everywhere All at Once
Introduces Benchmark Agent, a fully autonomous system for creating diverse benchmarks with minimal human intervention, enabling continuous model assessment across domains.