Benchmark Almanac

Ondřej Bojar

We track 2 benchmarks that Ondřej Bojar made or helped make.

0 in use 2 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
ImgMT Models translate text embedded in diagrams, maps, and infographics. Evaluation measures text recognition, region matching, and translation with CER, F1, chrF, and COMET. Translation Oct 2026 61.3 Not in cards
WMT 2016 News Translation Models translate news between languages. The harness compares translations with human references from the 2016 shared task. Translation Aug 2016 Not in cards