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
1Gemini 4 Carbontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.898
2Gemini 4 Hydrogentemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.881
3Gemini 3 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.864
4Gemini 3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.852
5Gemini 4 Neontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.852
6Gemini 4 Argontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.848
7Gemini 3.7 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.843
8Gemini 3.1 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.826
9GPT-6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.822
10Claude Opus 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.818
11Gemini 3.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.801
12Claude Sonnet 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.78
13Muse Spark 1.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.78
14Gemini 2.5 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.763
15DeepSeek V4.1 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.746
16Claude Sonnet 3.7temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.725
17DeepSeek V4 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.691
18Claude Opus 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.678
19DeepSeek V4 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.665
20GPT-5.6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.665
21GPT 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.631
22Mercury 2.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.627
23GPT 4otemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.606
24Claude Sonnet 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.585
25GLM 5.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.581
26GPT 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.576
27GLM 5.3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.568
28Grok 3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.568
29Gemini 2.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.559
30Claude Sonnet 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.555
31Gemini 2.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.555
32DeepSeek V3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.521
33Gemini 2.0 Flash Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.509
34Gemini 2.5 Flash-Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.504
35Gemma 4 31B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.504
36GPT-5 minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.5
37Qwen3.5 397B A17Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.5
38Ling 3.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.496
39GPT-4o minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.492
40Qwen3.5 122B-A10Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.479
41Gemma 4 26B A4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.475
42Claude Sonnet 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.47
43Llama 4 Scouttemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.47
44Grok 4.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.466
45GPT OSS 120Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.458
46Kimi K2 Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.449
47Claude Sonnet 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.441
48Qwen3 235B A22B Instruct 2507temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.436
49GLM 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.428
50Jev 1.13.0temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.428

Showing 1–50 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.