Skip to content

Benchmark

SeaLLMs SeaExam public (Vietnamese)

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models measured
57
Scores recorded
57
Sources
1
IQ weight
1.44

Score distribution

64.6%
Mean
66.9%
Median
12.3%
Std dev
50.7%
10th percentile
78.3%
90th percentile
31.2%
Min
31.2%90.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.44 for chat models, measured over 57 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 Pro Preview 03-25· SeaLLMs Leaderboard for SEA Languages data docs90.8%
2DeepSeek V3· SeaLLMs Leaderboard for SEA Languages data docs81.5%
3Claude Sonnet 3.7· SeaLLMs Leaderboard for SEA Languages data docs79.7%
4gemini-pro-1.5· SeaLLMs Leaderboard for SEA Languages data docs79.4%
5Claude 3.5 Sonnet· SeaLLMs Leaderboard for SEA Languages data docs79%
6Gemini 2.0 Flash· SeaLLMs Leaderboard for SEA Languages data docs78.5%
7Qwen2.5 72B· SeaLLMs Leaderboard for SEA Languages data docs78.3%
8Qwen2.5 72B Instruct· SeaLLMs Leaderboard for SEA Languages data docs78%
9GPT 4.1· SeaLLMs Leaderboard for SEA Languages data docs77.5%
10GPT 4o· SeaLLMs Leaderboard for SEA Languages data docs77.2%
11Gemma 3 27B Pt· SeaLLMs Leaderboard for SEA Languages data docs77.1%
12Gemini 2.0 Flash Lite· SeaLLMs Leaderboard for SEA Languages data docs76.5%
13Qwen 2 (72B)· SeaLLMs Leaderboard for SEA Languages data docs76.5%
14Qwen2 72B Instruct· SeaLLMs Leaderboard for SEA Languages data docs74.5%
15Qwen2.5 14B· SeaLLMs Leaderboard for SEA Languages data docs73.8%
16Gemini 1.5 Flash· SeaLLMs Leaderboard for SEA Languages data docs73.5%
17Llama 4 Maverick· SeaLLMs Leaderboard for SEA Languages data docs73.3%
18Gemma 3 27B IT· SeaLLMs Leaderboard for SEA Languages data docs73.1%
19Qwen 2.5 14B Instruct· SeaLLMs Leaderboard for SEA Languages data docs73.1%
20Llama 3.1 70B Instruct· SeaLLMs Leaderboard for SEA Languages data docs72.6%
21GPT-4.1 mini· SeaLLMs Leaderboard for SEA Languages data docs71.7%
22Gemma 2 27B IT· SeaLLMs Leaderboard for SEA Languages data docs70.1%
23Llama 3 70B Instruct· SeaLLMs Leaderboard for SEA Languages data docs69.1%
24Llama 3.1 70B· SeaLLMs Leaderboard for SEA Languages data docs68.3%
25Qwen2.5 7B· SeaLLMs Leaderboard for SEA Languages data docs68%
26Gemma 2 9B IT· SeaLLMs Leaderboard for SEA Languages data docs67.7%
27GPT-4o mini· SeaLLMs Leaderboard for SEA Languages data docs67%
28gemma2-27b· SeaLLMs Leaderboard for SEA Languages data docs66.9%
29Meta Llama 3 70b· SeaLLMs Leaderboard for SEA Languages data docs66.9%
30Qwen2.5 7B Instruct· SeaLLMs Leaderboard for SEA Languages data docs66.5%
31Claude Haiku 3.5· SeaLLMs Leaderboard for SEA Languages data docs66.1%
32Gemma 3 12B IT· SeaLLMs Leaderboard for SEA Languages data docs66.1%
33gemma-2-9b· SeaLLMs Leaderboard for SEA Languages data docs65.8%
34Llama 4 Scout· SeaLLMs Leaderboard for SEA Languages data docs65.5%
35Claude 3 Haiku· SeaLLMs Leaderboard for SEA Languages data docs63.7%
36GLM 4 9B 0414· SeaLLMs Leaderboard for SEA Languages data docs62.6%
37GPT-4.1 nano· SeaLLMs Leaderboard for SEA Languages data docs61.9%
38Qwen2 7B Instruct· SeaLLMs Leaderboard for SEA Languages data docs61.5%
39GLM-4-9b-chat· SeaLLMs Leaderboard for SEA Languages data docs61.4%
40Qwen2.5 3B Instruct· SeaLLMs Leaderboard for SEA Languages data docs60.6%
41Llama 3.1 8B Instruct· SeaLLMs Leaderboard for SEA Languages data docs57.6%
42Gemma 3 4B IT· SeaLLMs Leaderboard for SEA Languages data docs54.4%
43Llama 3.1 8B· SeaLLMs Leaderboard for SEA Languages data docs54.4%
44Aya Expanse 8B· SeaLLMs Leaderboard for SEA Languages data docs53.2%
45Mixtral 8X7b V0.1· SeaLLMs Leaderboard for SEA Languages data docs53.1%
46Qwen2.5 1.5B· SeaLLMs Leaderboard for SEA Languages data docs52.6%
47Llama 3 8B Instruct· SeaLLMs Leaderboard for SEA Languages data docs52.4%
48Meta Llama 3 8b· SeaLLMs Leaderboard for SEA Languages data docs52.4%
49Mixtral 8x7B Instruct v0.1· SeaLLMs Leaderboard for SEA Languages data docs52.2%
50Gemma 2 2B IT· SeaLLMs Leaderboard for SEA Languages data docs52%

Showing 1–50 of 57 results.

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