Benchmark Almanac

Los Angeles

We track 4 benchmarks that Los Angeles made or helped make.

0 in use 3 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Unsatz Agents design experiments and propose equations for an unknown simulated system. Their final program must predict held-out interventions and conditions beyond the original experiments. Research science Oct 2026 60% Not in cards
SciBench Models solve open-ended college-level problems in mathematics, chemistry and physics. Most answers are numbers, which a script checks against the key. Science questions Jul 2023 8.45% Not in cards
GD-VCR Models answer questions about what people are doing and why. The test pairs 328 images, mainly from film and television, with 886 questions across four regions. General visual questions Sep 2021 Not in cards
GeoMLAMA Models complete sentences about daily life in five countries. The test checks whether models rank locally correct answers above other choices in five languages. Knowledge in many languages May 2022 Not in cards