Benchmark
Bridging the Gap MMLU College Medicine Xhosa (xh) human-translated
Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.84
Score distribution
- 47.2%
- Mean
- 40.5%
- Median
- 16.9%
- Std dev
- 37%
- 10th percentile
- 78%
- 90th percentile
- 28.9%
- Min
This benchmark has a weight of 1.84 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 4otable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 78% |
| 2 | GPT-4 Turbotable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 61.3% |
| 3 | Llama 3 70B Instructtable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 40.5% |
| 4 | GPT-3.5 Turbotable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 37.6% |
| 5 | Llama 3 8B Instructtable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 37% |
| 6 | Phi-3 Mini 4K Instructtable: 2, task: MMLU College Medicine, language: xh, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 28.9% |
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)