Skip to content

Benchmark

ArmBench-LLM Armenian pioner (ner_accuracy, 0-shot)

Higher scores are better.

Models measured
27
Scores recorded
28
Sources
1
IQ weight
1.13

Score distribution

0.64
Mean
0.68
Median
0.139
Std dev
0.56
10th percentile
0.743
90th percentile
0.025
Min
0.0250.761
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.13 for chat models, measured over 27 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs0.761
2GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs0.761
3Grok 4 Fast· ArmBench-LLM Armenian data docs0.758
4Gemini 3 Pro Preview· ArmBench-LLM Armenian data docs0.743
5Grok 4.1 Fast· ArmBench-LLM Armenian data docs0.734
6Gemini 2.5 Pro· ArmBench-LLM Armenian data docs0.725
7Mistral Large 3· ArmBench-LLM Armenian data docs0.721
8Gemma 3 12B IT· ArmBench-LLM Armenian data docs0.704
9Gemini 2.5 Flash· ArmBench-LLM Armenian data docs0.703
10Gemma 4 31B IT· ArmBench-LLM Armenian data docs0.7
11Claude Sonnet 3.7· ArmBench-LLM Armenian data docs0.698
12Gemini 3 Flash· ArmBench-LLM Armenian data docs0.695
13Claude Sonnet 4· ArmBench-LLM Armenian data docs0.687
14Qwen3.5 27B· ArmBench-LLM Armenian data docs0.68
15Gemma 3 27B IT· ArmBench-LLM Armenian data docs0.676
16GLM 4.7 Flash· ArmBench-LLM Armenian data docs0.663
17GPT-5.4 mini· ArmBench-LLM Armenian data docs0.66
18Gemini 3.1 Pro Preview· ArmBench-LLM Armenian data docs0.658
19Grok 4.20· ArmBench-LLM Armenian data docs0.655
20Ministral 14B· ArmBench-LLM Armenian data docs0.621
21Mistral Small 3.2 24B Instruct· ArmBench-LLM Armenian data docs0.599
22GPT 5.4 Nano· ArmBench-LLM Armenian data docs0.585
23Gemma 3 4B IT· ArmBench-LLM Armenian data docs0.582
24Qwen3 4B Instruct 2507· ArmBench-LLM Armenian data docs0.577
25GLM 5· ArmBench-LLM Armenian data docs0.56
26Qwen3.5 35B A3B· ArmBench-LLM Armenian data docs0.521
27Qwen3 4B Base· ArmBench-LLM Armenian data docs0.482
28Qwen3.5 9B· ArmBench-LLM Armenian data docs0.025

Data credits: ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted.