Benchmark Almanac

University of Texas at Austin

We track 5 benchmarks that University of Texas at Austin made or helped make.

0 in use 4 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Realtime-Bench Agents act in 50 live game and web tasks where a late action fails: 30 web tasks (travel, shopping, services and security) and 20 games. The environment keeps moving while the model thinks. Three clocks separate speed from skill: Wall Clock runs on real time, Paused Clock stops while the model thinks, and Token Clock advances with each generated token. Scores are task success rates over three runs. Web browsing Oct 2026 42.7% Not in cards
AstroVisBench Models write code to process astronomical observations and plot the results. The benchmark compares computed values with reference outputs and uses a model to grade plots. Lab and data work May 2025 49.8% Not in cards
INQUISITIVE Models read a news article up to a highlighted phrase and ask a question a reader might have. Human raters judge validity, relevance, and salience. Reading comprehension Sep 2020 Not in cards
MultiCochrane Models rewrite medical review sentences in plain language. The collection pairs technical and simplified wording in English, Spanish, French, and Farsi. Medicine May 2023 Not in cards
VizWiz Models answer over 31,000 spoken questions that blind people asked about photos they took with phones. Some questions are unanswerable from the image. General visual questions Feb 2018 Not in cards