Benchmark
Bridging the Gap MMLU College Medicine Shona (sn) 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
- 1.96
Score distribution
- 47.8%
- Mean
- 38.7%
- Median
- 18.2%
- Std dev
- 35.8%
- 10th percentile
- 76.9%
- 90th percentile
- 28.3%
- Min
This benchmark has a weight of 1.96 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: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 76.9% |
| 2 | GPT-4 Turbotable: 2, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 68.8% |
| 3 | Llama 3 8B Instructtable: 2, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 38.7% |
| 4 | Llama 3 70B Instructtable: 2, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 38.2% |
| 5 | GPT-3.5 Turbotable: 2, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 35.8% |
| 6 | Phi-3 Mini 4K Instructtable: 2, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data | 28.3% |
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)