Skip to content

Benchmark

SeaLLMs SeaBench private (Vietnamese)

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

Models measured
32
Scores recorded
32
Sources
1
IQ weight
2.02

Score distribution

7.6
Mean
7.8
Median
1.2
Std dev
5.9
10th percentile
8.8
90th percentile
3.7
Min
3.78.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.02 for chat models, measured over 32 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 4.1judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.9
2DeepSeek V3judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.9
3Claude 3.5 Sonnetjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.8
4Claude Sonnet 3.7judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.8
5Gemini 2.0 Flashjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.8
6GPT 4ojudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.7
7gemini-pro-1.5judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.6
8GPT-4.1 minijudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.6
9GPT-4o minijudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.5
10Gemma 3 27B ITjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.5
11Gemini 2.0 Flash Litejudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.3
12Gemma 3 12B ITjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.2
13Qwen2.5 72B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.1
14Gemini 1.5 Flashjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs8.1
15Claude Haiku 3.5judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.9
16Gemma 2 27B ITjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.8
17Llama 4 Maverickjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.8
18GPT-4.1 nanojudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.8
19Qwen 2.5 14B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.5
20Qwen2 72B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.4
21Claude 3 Haikujudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.4
22Gemma 2 9B ITjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.3
23Llama 3 70B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.1
24Qwen2.5 7B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7.1
25Gemma 3 4B ITjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs7
26Llama 3.1 70B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs6.9
27Llama 4 Scoutjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs6.6
28GLM-4-9b-chatjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs6.5
29Qwen2 7B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs5.9
30Llama 3.1 8B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs5.8
31Qwen2.5 3B Instructjudge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs5.4
32Mistral (7B) Instruct v0.3judge:GPT-4o-2024-08-06· SeaLLMs Leaderboard for SEA Languages data docs3.7

Data credits: SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated.