Claude Opus 5.5 is the new #1 on Multilingual Terminal-Bench, the coding benchmark on AURORA, our multilingual AI leaderboard. Oct 8
Introducing AURORA: A Multilingual Leaderboard for Frontier Models on Non-English Agentic Tasks Sep 30
Introducing Terminal-Bench-LILT: Multilingual Agentic Benchmark Grounded in Language, Region, and Culture Sep 8
LILTBench Hackathon (Jun 2026) One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. LILTBench Hackathon (Jun 2026) Collection One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. • 1 item • Updated Jun 8
LILTBench Hackathon (Jun 2026) Collection One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. • 1 item • Updated Jun 8
LILTBench Hackathon (Jun 2026) One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. LILTBench Hackathon (Jun 2026) Collection One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. • 1 item • Updated Jun 8
LILTBench Hackathon (Jun 2026) Collection One-week community hackathon (Jun 15–21, 2026) to crowdsource deterministic coding tasks that expose where frontier models fail outside English. • 1 item • Updated Jun 8
