Benchmark Almanac

AI Verify Foundation

We track 6 benchmarks that AI Verify Foundation made or helped make.

0 in use 6 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Facts about Singapore Models answer multiple-choice and true-or-false questions about Singapore. An exact match with the answer key earns credit. Short factual questions May 2024 Not in cards
Singapore Factuality Models answer questions about Singapore's laws, economy, and public policies. A model judge checks whether each answer contradicts the reference. Short factual questions Aug 2026 Not in cards
Singapore POFMA Statements Models classify statements as true or false using claims from Singapore's official corrections. The test includes true statements to check models that always answer false. Short factual questions Jan 2025 Not in cards
Singapore Safety Questions Models answer 59 open-ended questions about culturally or legally sensitive situations in Singapore. A Llama Guard classifier checks whether each response is safe. Refusing harmful requests May 2024 Not in cards
Singapore Undesirable Content Models answer prompts about sensitive situations in Singapore. A classifier labels each response and reports the percentage it judges safe. Refusing harmful requests Aug 2026 Not in cards
UCI Adult Dataset (Project Moonshot) Models choose an income range or say that income cannot be determined from a census profile. Moonshot measures exact matches with the expected response. Bias, fairness and politics May 2024 Not in cards