Skip to content

Benchmark

ArmBench-LLM Armenian topic-14class (exact_match_mcqa, 0-shot)

Higher scores are better.

Models measured
27
Scores recorded
28
Sources
1
IQ weight
1.72

Score distribution

0.527
Mean
0.564
Median
0.121
Std dev
0.479
10th percentile
0.593
90th percentile
0
Min
00.596
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.72 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
1Claude Sonnet 4· ArmBench-LLM Armenian data docs0.596
2Gemini 3 Pro Preview· ArmBench-LLM Armenian data docs0.593
3GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs0.593
4GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs0.593
5Gemini 3.1 Pro Preview· ArmBench-LLM Armenian data docs0.589
6Gemini 3 Flash· ArmBench-LLM Armenian data docs0.586
7Gemma 4 31B IT· ArmBench-LLM Armenian data docs0.586
8Claude Sonnet 3.7· ArmBench-LLM Armenian data docs0.579
9GPT-5.4 mini· ArmBench-LLM Armenian data docs0.575
10Grok 4 Fast· ArmBench-LLM Armenian data docs0.575
11Grok 4.1 Fast· ArmBench-LLM Armenian data docs0.575
12GLM 5· ArmBench-LLM Armenian data docs0.571
13Mistral Large 3· ArmBench-LLM Armenian data docs0.568
14Gemma 3 12B IT· ArmBench-LLM Armenian data docs0.564
15Qwen3.5 27B· ArmBench-LLM Armenian data docs0.564
16Gemini 2.5 Flash· ArmBench-LLM Armenian data docs0.561
17Gemini 2.5 Pro· ArmBench-LLM Armenian data docs0.557
18GLM 4.7 Flash· ArmBench-LLM Armenian data docs0.557
19Qwen3.5 35B A3B· ArmBench-LLM Armenian data docs0.55
20GPT 5.4 Nano· ArmBench-LLM Armenian data docs0.543
21Mistral Small 3.2 24B Instruct· ArmBench-LLM Armenian data docs0.539
22Gemma 3 27B IT· ArmBench-LLM Armenian data docs0.521
23Ministral 14B· ArmBench-LLM Armenian data docs0.521
24Gemma 3 4B IT· ArmBench-LLM Armenian data docs0.496
25Qwen3.5 9B· ArmBench-LLM Armenian data docs0.479
26Qwen3 4B Instruct 2507· ArmBench-LLM Armenian data docs0.464
27Qwen3 4B Base· ArmBench-LLM Armenian data docs0.254
28Grok 4.20· ArmBench-LLM Armenian data docs0

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