Releases: callstackincubator/evals
Releases · callstackincubator/evals
2 new categories and 4 new models
We've added 2 new categories (lists, react-native-apis) and 4 new models (claude-opus-4.7, composer-2-fast, gemma-4-31B-it, minimax-m2.7)
Composer-2 benchmark & full generated data
We've added Composer 2 model from Cursor to the benchmark and published all model benchmark artifacts