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
51Llama 3.3 70B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.389
52Qwen3 235B A22B Instruct 2507temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.389
53Qwen3.5 122B-A10Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.375
54GPT OSS 120Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.361
55Mistral Nemotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.361
56Qwen3 32Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.361
57Qwen3 8Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.361
58Gemma 3n E4B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.347
59Llama 3.1 8B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.347
60Qwen3 4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.347
61Qwen3.5 35B A3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.333
62Qwen3 14Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.319
63GPT OSS 20btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.306
64Qwen 3.8 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.306
65Qwen3.5 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.306
66Llama 4 Mavericktemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.292
67Qwen3.5 397B A17Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.292
68Mistral (7B) Instruct v0.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.264
69Claude Sonnet 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.25
70Llama 3.2 1B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.25
71Phi 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.236
72Qwen3.5 9Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.222
73Llama 3.2 3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.208
74Claude Sonnet 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.194

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.