benchmark · first seen 13 Oct 2026
LiveCodeBench
A contamination-resistant benchmark for evaluating code generation using recently published programming problems.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Beyond Functional Correctness: Static Code Quality Profiling of LLM-Generated CodePapers · 13 Oct 2026 · Jue Huang, Tarek Mahmud, Meiru Che, Guowei Yang
- Test-Time Self-Play: Scaling without a VerifierPapers · 5 Nov 2026 · Akira Yoshiyama, Akmal Ashirmatov, Jonas Hübotter, Ido Hakimi, Andreas Krause
Latest sources
- Test-Time Self-Play: Scaling without a VerifierPapers · 5 Nov 2026 · Akira Yoshiyama, Akmal Ashirmatov, Jonas Hübotter, Ido Hakimi, Andreas Krause
- Beyond Functional Correctness: Static Code Quality Profiling of LLM-Generated CodePapers · 13 Oct 2026 · Jue Huang, Tarek Mahmud, Meiru Che, Guowei Yang