Benchmark
KazBench Kazakh knowledge_mc (accuracy, dev)
Higher scores are better.
Benchmark sourceScores from KazBench Kazakh data docs.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.07
Score distribution
- 0.897
- Mean
- 0.96
- Median
- 0.085
- Std dev
- 0.88
- 10th percentile
- 0.96
- 90th percentile
- 0.72
- Min
This benchmark has a weight of 1.07 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 | 0.96 |
| 2 | GPT-4o minidev, version: 0.1.0· KazBench Kazakh data docs | 0.96 |
| 3 | Llama 4 Scoutdev, version: 0.1.0· KazBench Kazakh data docs | 0.96 |
| 4 | Gemini 2.5 Flashdev, version: 0.1.0· KazBench Kazakh data docs | 0.9 |
| 5 | Qwen2.5 72B Instructdev, version: 0.1.0· KazBench Kazakh data docs | 0.88 |
| 6 | Llama 3.1 8B Instantdev, version: 0.1.0· KazBench Kazakh data docs | 0.72 |