Google DeepMind

Code Generation QA

How AlphaCode 2 Uses Gemini to Solve 43% of Codeforces

Inside Google DeepMind's AlphaCode 2: how Gemini Pro, million-sample generation, and execution-based filtering hit the 85th percentile on Codeforces.

Code Generation QA

AlphaCode Explained: How DeepMind Tests AI-Written Code

How DeepMind's AlphaCode reached the top 54.3% on Codeforces and built CodeContests to validate AI-generated code against hidden tests, not luck.

Code Generation QA

How AlphaCode Tested AI Code on Codeforces

How DeepMind benchmarked AlphaCode on 10 Codeforces contests with a generate-filter-cluster-rerank pipeline, and what it teaches AI code QA.

Code Generation QA

MBPP: How Google Tests LLM Code Generation

How Google's MBPP benchmark grades AI-generated Python by execution, not text similarity, across model scales from 244M to 137B parameters.