Skip to content

Benchmark

Bridging the Gap Belebele Bambara (bm) human-translated

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

Models and systems measured
30
Scores recorded
32
Sources
1
IQ weight
0.87

Score distribution

32.6%
Mean
32.2%
Median
2.3%
Std dev
29.8%
10th percentile
35.6%
90th percentile
29%
Min
29%38.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.87 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 or systemScore
1GPT 4otable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data38.3%
2GPT-4 Turbotable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data37.9%
3Llama 3 70B Instructtable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data35.6%
4Llama 3 8B Instructtable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data32%
5Phi-3 Mini 4K Instructtable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.7%
6GPT-3.5 Turbotable: 2, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data30.6%

Not ranked

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

Model or systemScore
Llama 3 70B Instructtable: A.26, row: base, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data35.6%
Llama 3 70B Instructtable: A.27, row: base, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data35.6%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: aftable: A.26, training: Winogrande train (small), trainingLanguage: af, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data33.6%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: amtable: A.26, training: Winogrande train (small), trainingLanguage: am, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data34.9%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: bmtable: A.26, training: Winogrande train (small), trainingLanguage: bm, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data29%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: entable: A.26, training: Winogrande train (small), trainingLanguage: en, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data33.4%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: igtable: A.26, training: Winogrande train (small), trainingLanguage: ig, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data29.8%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: nsotable: A.26, training: Winogrande train (small), trainingLanguage: nso, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data30.2%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: sntable: A.26, training: Winogrande train (small), trainingLanguage: sn, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data33.3%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: sttable: A.26, training: Winogrande train (small), trainingLanguage: st, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data32.2%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: tntable: A.26, training: Winogrande train (small), trainingLanguage: tn, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.6%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: tstable: A.26, training: Winogrande train (small), trainingLanguage: ts, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data29.3%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: xhtable: A.26, training: Winogrande train (small), trainingLanguage: xh, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data29.7%
Llama 3 70B ITLoRA, dataset: Winogrande train (small), language: zutable: A.26, training: Winogrande train (small), trainingLanguage: zu, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data30.9%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: aftable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: af, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data30.8%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: amtable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: am, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data33.1%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: bmtable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: bm, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data32.8%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: entable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: en, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data33.6%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: igtable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: ig, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data32.5%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: nsotable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: nso, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.4%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: sntable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: sn, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data34.5%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: sttable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: st, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data32.9%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: tntable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: tn, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: tstable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: ts, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.1%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: xhtable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: xh, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.3%
Llama 3 70B ITLoRA, dataset: MMLU College Medicine dev + test + val, language: zutable: A.27, training: MMLU College Medicine dev + test + val, trainingLanguage: zu, task: Belebele, language: bm, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data31.5%

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)