Skip to content

Benchmark

IdrockBench Uzbek Zarbulmasal riddles (free-text exact match, task v1.0)

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

Models measured
12
Scores recorded
12
Sources
1
IQ weight
1.81

Score distribution

6.7%
Mean
3.3%
Median
8.1%
Std dev
0%
10th percentile
16.9%
90th percentile
0%
Min
0%25.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.81 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 docs25.7%
2Qwen3.6 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs16.9%
3Gemma 4 26BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs12.7%
4Qwen 3.8 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs10.6%
5Qwen3.5 27BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs9.4%
6gemma 4 E4BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs3.3%
7Qwen3.5 9BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs1.8%
8Qwen3.5 4BQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs0.3%
9Gemma 4 E2B ITQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs0%
10Nemotron 3.5 Lightning 30bQ4_K_M, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs0%
11Qwen3.5 0.8BQ8_0, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs0%
12Qwen3.5 2BQ8_0, reasoning: off, organiser-run· IdrockBench Uzbek leaderboard data docs0%

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