University of Zurich
We track 7 benchmarks that University of Zurich made or helped make.
0 in use 4 with public code 3 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| LEXam Models answer 7,537 questions from 340 law exams at Swiss, EU and international law courses, in English and German. Open answers are judged against reference answers, and multiple-choice items are exact match. | Law | May 2025 | 70.2% | Not in cards |
| BenchMAX Models follow instructions, write code, reason, use tools, translate, and retrieve information across 17 languages. Ten tasks use rule checks, model-judged wins, code tests, answer matching, or translation scores. | Reasoning in many languages | Feb 2025 | | Not in cards |
| AD4Edu-Bench Models write audio descriptions for university lectures. A rubric checks accessibility rules, and the authors compare the rankings with blind and low-vision listeners' preferences. | Video captioning | Oct 2026 | | Not in cards |
| CT-RATE Models read 3D non-contrast chest CT volumes and say whether each of 18 conditions is present. Scored by macro accuracy or F1 against report-derived labels. | Medicine | Mar 2024 | Not in cards | |
| Med-EASi Models rewrite English medical passages in plain language. The references mark replacements, explanations, insertions, and deletions. | Medicine | Feb 2023 | Not in cards | |
| Swiss Job Market Monitor ICT Term Recognition Models mark words for information and communication technology in German-language Swiss job ads. The original test holds out 10% of the annotated ads. | Other professions | May 2022 | Not in cards | |
| Universal Dependencies Sanskrit Vedic Models identify which word governs each word in Vedic Sanskrit and label the grammatical relation. The official split keeps each hymn or prose chapter together. | Reading in many languages | May 2020 | Not in cards |