Skip to content

Benchmark

UzLiB overall accuracy (all items)

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

Models measured
74
Scores recorded
74
Sources
1
IQ weight
1.26

Score distribution

0.562
Mean
0.548
Median
0.154
Std dev
0.375
10th percentile
0.795
90th percentile
0.233
Min
0.2330.852
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 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 docs0.852
2Gemini 4 Argontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.844
3Gemini 4 Neontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.842
4Gemini 3 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.826
5Gemini 4 Hydrogentemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.823
6Gemini 3.7 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.809
7GPT-6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.809
8Gemini 3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.795
9Gemini 3.1 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.782
10Claude Sonnet 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.781
11Muse Spark 1.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.778
12Claude Opus 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.774
13Gemini 3.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.761
14DeepSeek V4.1 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.748
15GPT-5.6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.714
16DeepSeek V4 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.709
17Gemini 2.5 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.691
18GPT 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.662
19Claude Sonnet 3.7temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.651
20DeepSeek V4 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.646
21Claude Sonnet 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.641
22GPT 4otemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.632
23Mercury 2.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.63
24Gemini 2.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.626
25GPT 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.616
26Claude Sonnet 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.615
27GLM 5.3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.615
28GLM 5.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.611
29Gemini 2.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.601
30Claude Opus 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.6
31Gemini 2.0 Flash Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.586
32Gemini 2.5 Flash-Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.572
33Grok 4.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.564
34Gemma 4 31B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.554
35Llama 4 Scouttemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.552
36GPT OSS 120Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.549
37Gemma 4 26B A4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.548
38DeepSeek V3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.544
39GLM 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.538
40GPT-5 minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.529
41GPT-4o minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.526
42MiMo V2 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.523
43Kimi K2 Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.518
44Grok 3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.515
45Ling 3.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.514
46Jev 1.13.0temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.505
47Claude Sonnet 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.505
48GLM 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.498
49Gemma 3 27B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.495
50GPT-5 nanotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.493

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.