Skip to content

Benchmark

KazBench Kazakh sentiment (accuracy, dev)

Higher scores are better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.80

Score distribution

0.882
Mean
0.961
Median
0.136
Std dev
0.843
10th percentile
1
90th percentile
0.608
Min
0.6081
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.80 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

#ModelScore
1Gemini 2.5 Flashdev, version: 0.1.0· KazBench Kazakh data docs1
2Llama 4 Scoutdev, version: 0.1.0· KazBench Kazakh data docs1
3GPT-4o minidev, version: 0.1.0· KazBench Kazakh data docs0.961
4Claude Haiku 3.5dev, version: 0.1.0· KazBench Kazakh data docs0.882
5Qwen2.5 72B Instructdev, version: 0.1.0· KazBench Kazakh data docs0.843
6Llama 3.1 8B Instantdev, version: 0.1.0· KazBench Kazakh data docs0.608

Data credits: KazBench by Yersultan Akhmer. Provisional DEV numeric results; code MIT and task-data CC BY 4.0 do not establish a separate score licence.