Benchmark
Bridging the Gap Virology Tsonga (ts) human-translation minus back-translation difference
Multilingual benchmarks compare model performance across languages.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- -11.3
- Mean
- -10.9
- Median
- 3.7
- Std dev
- -14.5
- 10th percentile
- -4.2
- 90th percentile
- -15.7
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model | Score |
|---|---|
| GPT 4otable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -4.2 |
| GPT-3.5 Turbotable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -14.5 |
| GPT-4 Turbotable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -10.8 |
| Llama 3 70B Instructtable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -15.7 |
| Llama 3 8B Instructtable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -11.5 |
| Phi-3 Mini 4K Instructtable: A.14, section: back-translation-difference, task: MMLU Virology, language: ts, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | -10.9 |
Data credits: Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin and Guillaume Chabot-Couture. Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments, arXiv:2412.12417v1. CC BY 4.0 article numeric/protocol extract, restructured with values unchanged. No task or model rights asserted. (licence)