Terminal-Bench Challenges

Single-task challenge leaderboards for inference engine code golf, Rust compiler speedup, and WASM rendering.

Inference Engine Code Golf

1.0coming soon

Single-task challenge: write a complete Kimi K2.5 inference engine in one <=25,000-byte CUDA file. Leaderboard rolling out shortly.

Rust Compiler Speedup

1.0coming soon

Single-task challenge: make rustc compile programs faster while preserving full-suite correctness. Leaderboard rolling out shortly.

WASM Render

1.0coming soon

Single-task challenge: implement a pure JS/WASM WebGL 1.0 and 2.0 software renderer. Leaderboard rolling out shortly.