Skip to content

Benchmark

UzLiB correct word accuracy

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

Models measured
74
Scores recorded
74
Sources
1
IQ weight
1.32

Score distribution

0.572
Mean
0.566
Median
0.15
Std dev
0.38
10th percentile
0.794
90th percentile
0.229
Min
0.2290.845
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.32 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
51Grok 3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.508
52Qwen3 235B A22B Instruct 2507temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.504
53Gemma 3 12B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.491
54GPT OSS 20btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.484
55Qwen3 32Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.472
56Qwen3.5 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.47
57Gemma 3n E4B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.462
58Qwen3.5 9Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.46
59Llama 3.3 70B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.447
60Mistral Nemotemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.434
61C4AI Command A 03 2025temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.428
62Qwen3.5 122B-A10Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.414
63Qwen 3.8 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.408
64Qwen3.5 397B A17Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.402
65Qwen3 8Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.4
66Llama 3.1 8B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.394
67Qwen3 14Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.38
68Qwen3.5 35B A3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.38
69Qwen3 4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.351
70Phi 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.347
71Mistral (7B) Instruct v0.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.343
72Llama 3.2 3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.276
73Llama 4 Mavericktemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.266
74Llama 3.2 1B Instructtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.229

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.