Skip to content

Benchmark

ArmBench-LLM Armenian email (bleu, 0-shot)

Higher scores are better.

Models measured
27
Scores recorded
28
Sources
1
IQ weight
0.50

Score distribution

12.7
Mean
12.9
Median
5
Std dev
7.1
10th percentile
18.6
90th percentile
0.00000447
Min
0.0000044721.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.50 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
1Gemini 2.5 Flash· ArmBench-LLM Armenian data docs21.2
2Claude Sonnet 3.7· ArmBench-LLM Armenian data docs20.9
3Claude Sonnet 4· ArmBench-LLM Armenian data docs20
4Grok 4.1 Fast· ArmBench-LLM Armenian data docs18.6
5Grok 4 Fast· ArmBench-LLM Armenian data docs17.1
6GPT-5.4 mini· ArmBench-LLM Armenian data docs16.2
7GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs15.8
8GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs15.8
9Gemma 3 27B IT· ArmBench-LLM Armenian data docs15.4
10Gemma 3 12B IT· ArmBench-LLM Armenian data docs14.9
11GPT 5.4 Nano· ArmBench-LLM Armenian data docs14.6
12Mistral Large 3· ArmBench-LLM Armenian data docs13.6
13Gemma 4 31B IT· ArmBench-LLM Armenian data docs13.5
14GLM 5· ArmBench-LLM Armenian data docs12.9
15Qwen3.5 27B· ArmBench-LLM Armenian data docs12.7
16Ministral 14B· ArmBench-LLM Armenian data docs12
17Gemini 3 Pro Preview· ArmBench-LLM Armenian data docs11.8
18Gemini 3 Flash· ArmBench-LLM Armenian data docs11.8
19Gemma 3 4B IT· ArmBench-LLM Armenian data docs11.4
20Gemini 2.5 Pro· ArmBench-LLM Armenian data docs11
21GLM 4.7 Flash· ArmBench-LLM Armenian data docs10.9
22Gemini 3.1 Pro Preview· ArmBench-LLM Armenian data docs10.8
23Qwen3 4B Instruct 2507· ArmBench-LLM Armenian data docs9.8
24Mistral Small 3.2 24B Instruct· ArmBench-LLM Armenian data docs8.8
25Qwen3 4B Base· ArmBench-LLM Armenian data docs7.1
26Grok 4.20· ArmBench-LLM Armenian data docs4.4
27Qwen3.5 35B A3B· ArmBench-LLM Armenian data docs2.7
28Qwen3.5 9B· ArmBench-LLM Armenian data docs0.00000447

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