Benchmark
KazBench Kazakh reading_comprehension (accuracy, dev)
Higher scores are better.
Benchmark sourceScores from KazBench Kazakh data docs.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.53
Score distribution
- 0.969
- Mean
- 1
- Median
- 0.045
- Std dev
- 0.958
- 10th percentile
- 1
- 90th percentile
- 0.875
- Min
This benchmark has a weight of 0.53 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 | Claude Haiku 3.5dev, version: 0.1.0· KazBench Kazakh data docs | 1 |
| 2 | Gemini 2.5 Flashdev, version: 0.1.0· KazBench Kazakh data docs | 1 |
| 3 | GPT-4o minidev, version: 0.1.0· KazBench Kazakh data docs | 1 |
| 4 | Qwen2.5 72B Instructdev, version: 0.1.0· KazBench Kazakh data docs | 0.979 |
| 5 | Llama 3.1 8B Instantdev, version: 0.1.0· KazBench Kazakh data docs | 0.958 |
| 6 | Llama 4 Scoutdev, version: 0.1.0· KazBench Kazakh data docs | 0.875 |