Benchmark
Irish-BLiMP per-category score standard deviation
Multilingual benchmarks compare model performance across languages.
- Models and systems measured
- 10
- Scores recorded
- 10
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 7.6
- Mean
- 7.7
- Median
- 1.9
- Std dev
- 5.5
- 10th percentile
- 8.6
- 90th percentile
- 5.4
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| claude-sonnet-4.5table: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 12.2 |
| gemini-2.5-flash-litetable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 8.6 |
| gemma-3-27b-ittable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 8.2 |
| gpt-5table: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 8.4 |
| gpt-oss-120btable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 6.5 |
| gpt-oss-20btable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 5.5 |
| Llama-2-13btable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 7.7 |
| Llama-4-Scout-17B-16E-Instr.table: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 6 |
| Mistral-Small-3.2-24B-Instr.table: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 5.4 |
| UCCIXtable: 2· Irish-BLiMP (arXiv:2510.20957v1) data | 7.6 |
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)