Benchmark
PashtoBench factual QA exact match English-minus-Pashto delta
Multilingual benchmarks compare model performance across languages.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- -0.006
- Mean
- 0
- Median
- 0.011
- Std dev
- -0.025
- 10th percentile
- 0
- 90th percentile
- -0.025
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model | Score |
|---|---|
| Claude Sonnet 5column: EM delta· PashtoBench v1.0 data docs | 0 |
| GPT 4ocolumn: EM delta· PashtoBench v1.0 data docs | 0 |
| Llama 3.3 70B Instructcolumn: EM delta· PashtoBench v1.0 data docs | -0.025 |
| Qwen2.5 72B Instructcolumn: EM delta· PashtoBench v1.0 data docs | 0 |