Skip to content

Benchmark

UzLiB meaning in context accuracy

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

Models measured
74
Scores recorded
74
Sources
1
IQ weight
0.90

Score distribution

0.53
Mean
0.528
Median
0.202
Std dev
0.292
10th percentile
0.833
90th percentile
0.194
Min
0.1940.917
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.90 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 Hydrogentemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.917
2Gemini 4 Neontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.917
3Gemini 4 Argontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.903
4Gemini 4 Carbontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.903
5GPT-6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.903
6Gemini 3 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.875
7Gemini 3.7 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.847
8Claude Opus 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.833
9Claude Sonnet 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.792
10Gemini 2.5 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.778
11GPT-5.6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.764
12Gemini 2.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.736
13Claude Sonnet 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.722
14DeepSeek V4.1 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.722
15Claude Sonnet 3.7temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.708
16DeepSeek V4 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.708
17Gemini 3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.708
18GPT 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.708
19Muse Spark 1.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.708
20Gemini 3.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.694
21DeepSeek V4 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.694
22Gemini 3.1 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.694
23Claude Sonnet 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.681
24GPT 4otemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.653
25Gemini 2.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.639
26Grok 4.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.639
27Mercury 2.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.597
28Gemini 2.0 Flash Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.583
29Gemma 4 31B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.583
30GLM 5.3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.583
31Grok 3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.583
32Jev 1.13.0temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.583
33Llama 4 Scouttemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.556
34GLM 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.542
35GLM 5.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.542
36GPT 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.542
37DeepSeek V3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.528
38Gemini 2.5 Flash-Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.528
39GLM 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.5
40GPT-5 minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.486
41Kimi K2 Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.472
42Gemma 3 12B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.444
43Gemma 4 26B A4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.444
44Claude Opus 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.431
45GPT-4o minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.431
46GPT-5 nanotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.403
47Ling 3.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.403
48MiMo V2 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.403
49C4AI Command A 03 2025temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.389
50Gemma 3 27B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.389

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.