Skip to content

Benchmark

Irish-BLiMP accuracy (zero-shot; §5.1)

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models and systems measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

70.3%
Mean
73.5%
Median
3.2%
Std dev
67.1%
10th percentile
73.5%
90th percentile
67.1%
Min
67.1%73.5%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
gemini-2.5-flash-liteprompting: zero-shot, context: §5.1, source: prose· Irish-BLiMP (arXiv:2510.20957v1) data67.1%
gpt-5prompting: zero-shot, context: §5.1, source: prose· Irish-BLiMP (arXiv:2510.20957v1) data73.5%

Data credits: Josh McGiff, Khanh-Tung Tran, William Mulcahy, Dáibhidh Ó Luinín, Jake Dalzell, Róisín Ní Bhroin, Adam Burke, Barry O'Sullivan, Hoang D. Nguyen and Nikola S. Nikolov. Irish-BLiMP, arXiv:2510.20957v1, submitted 2025-10-23. CC BY 4.0 article numeric/protocol extract; restructured, printed values unchanged. No task, prompt or model rights asserted. (licence)