Skip to content

Benchmark

ArmBench-LLM Armenian syndarin (exact_match_mcqa, 0-shot)

Higher scores are better.

Models measured
27
Scores recorded
28
Sources
1
IQ weight
1.13

Score distribution

0.892
Mean
0.96
Median
0.225
Std dev
0.84
10th percentile
1
90th percentile
0.04
Min
0.041
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
1Claude Sonnet 4· ArmBench-LLM Armenian data docs1
2Gemini 2.5 Flash· ArmBench-LLM Armenian data docs1
3Gemini 2.5 Pro· ArmBench-LLM Armenian data docs1
4Gemini 3 Flash· ArmBench-LLM Armenian data docs1
5Gemini 3.1 Pro Preview· ArmBench-LLM Armenian data docs1
6Gemma 4 31B IT· ArmBench-LLM Armenian data docs1
7GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs1
8GPT-5.2 Prosetting not named by the source· ArmBench-LLM Armenian data docs1
9Claude Sonnet 3.7· ArmBench-LLM Armenian data docs0.98
10Gemini 3 Pro Preview· ArmBench-LLM Armenian data docs0.98
11GPT 5.4 Nano· ArmBench-LLM Armenian data docs0.98
12GLM 5· ArmBench-LLM Armenian data docs0.96
13Grok 4 Fast· ArmBench-LLM Armenian data docs0.96
14Mistral Large 3· ArmBench-LLM Armenian data docs0.96
15Qwen3.5 27B· ArmBench-LLM Armenian data docs0.96
16Gemma 3 27B IT· ArmBench-LLM Armenian data docs0.94
17GLM 4.7 Flash· ArmBench-LLM Armenian data docs0.94
18GPT-5.4 mini· ArmBench-LLM Armenian data docs0.94
19Grok 4.1 Fast· ArmBench-LLM Armenian data docs0.94
20Ministral 14B· ArmBench-LLM Armenian data docs0.94
21Qwen3 4B Instruct 2507· ArmBench-LLM Armenian data docs0.94
22Gemma 3 4B IT· ArmBench-LLM Armenian data docs0.92
23Gemma 3 12B IT· ArmBench-LLM Armenian data docs0.9
24Qwen3.5 35B A3B· ArmBench-LLM Armenian data docs0.9
25Qwen3.5 9B· ArmBench-LLM Armenian data docs0.84
26Mistral Small 3.2 24B Instruct· ArmBench-LLM Armenian data docs0.8
27Qwen3 4B Base· ArmBench-LLM Armenian data docs0.16
28Grok 4.20· ArmBench-LLM Armenian data docs0.04

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