Skip to content

Benchmark

UzLiB meaning accuracy

Multilingual benchmarks compare model performance across languages. Higher scores are better.

Models measured
74
Scores recorded
74
Sources
1
IQ weight
1.25

Score distribution

0.534
Mean
0.5
Median
0.181
Std dev
0.322
10th percentile
0.826
90th percentile
0.25
Min
0.250.898
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.25 for chat models, measured over 73 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Gemma 3 27B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.424
52GLM 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.403
53Qwen3 32Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.403
54Qwen3.5 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.398
55Qwen3.5 35B A3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.398
56GPT OSS 20btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.39
57Gemma 3 12B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.381
58C4AI Command A 03 2025temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.377
59MiMo V2 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.377
60Qwen3 14Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.377
61Llama 4 Mavericktemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.364
62Llama 3.3 70B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.36
63Qwen 3.8 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.356
64GPT-5 nanotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.348
65Gemma 3n E4B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.343
66Qwen3.5 9Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.343
67Phi 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.322
68Qwen3 4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.309
69Llama 3.1 8B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.305
70Qwen3 8Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.292
71Mistral Nemotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.288
72Mistral (7B) Instruct v0.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.254
73Llama 3.2 1B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.25
74Llama 3.2 3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.25

Showing 51–74 of 74 results.

Data credits: UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted.