Skip to content

Benchmark

IdrockBench Uzbek DTM entrance-exam knowledge (accuracy, task v2.1)

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

Models measured
12
Scores recorded
12
Sources
1
IQ weight
0.87

Score distribution

39.2%
Mean
37%
Median
10.6%
Std dev
25.9%
10th percentile
52.4%
90th percentile
25.8%
Min
25.8%57%
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 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemma 4 31B ITQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs57%
2Qwen3.5 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs52.4%
3Qwen3.6 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs50.3%
4Gemma 4 26BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs48.5%
5Qwen 3.8 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs45.9%
6Qwen3.5 9BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs37%
7gemma 4 E4BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs32.8%
8Nemotron 3.5 Lightning 30bQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs32.5%
9Qwen3.5 4BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs32.2%
10Gemma 4 E2B ITQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs29.5%
11Qwen3.5 0.8BQ8_0, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs25.9%
12Qwen3.5 2BQ8_0, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs25.8%

Data credits: IdrockBench, IDROCK AI Excellence Center, New Uzbekistan University. Public numeric results; no results licence stated (code MIT and dataset licences not borrowed).