Skip to content

Benchmark

SeaLLMs SeaExam private (Thai)

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

Models measured
57
Scores recorded
57
Sources
1
IQ weight
1.41

Score distribution

54.2%
Mean
57.6%
Median
14.8%
Std dev
37.1%
10th percentile
71.8%
90th percentile
24.9%
Min
24.9%94.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.41 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 docs94.2%
2Claude 3.5 Sonnet· SeaLLMs Leaderboard for SEA Languages data docs76%
3Claude Sonnet 3.7· SeaLLMs Leaderboard for SEA Languages data docs74.1%
4gemini-pro-1.5· SeaLLMs Leaderboard for SEA Languages data docs73.9%
5DeepSeek V3· SeaLLMs Leaderboard for SEA Languages data docs73.7%
6Gemini 2.0 Flash· SeaLLMs Leaderboard for SEA Languages data docs73.2%
7Llama 4 Maverick· SeaLLMs Leaderboard for SEA Languages data docs71.8%
8Qwen2.5 72B· SeaLLMs Leaderboard for SEA Languages data docs71.3%
9Qwen 2 (72B)· SeaLLMs Leaderboard for SEA Languages data docs69.7%
10GPT 4o· SeaLLMs Leaderboard for SEA Languages data docs69.5%
11Qwen2.5 72B Instruct· SeaLLMs Leaderboard for SEA Languages data docs68.8%
12GPT 4.1· SeaLLMs Leaderboard for SEA Languages data docs68.5%
13Gemini 2.0 Flash Lite· SeaLLMs Leaderboard for SEA Languages data docs67.4%
14Gemini 1.5 Flash· SeaLLMs Leaderboard for SEA Languages data docs65.7%
15Qwen2.5 14B· SeaLLMs Leaderboard for SEA Languages data docs65%
16GPT-4.1 mini· SeaLLMs Leaderboard for SEA Languages data docs64.8%
17Qwen2 72B Instruct· SeaLLMs Leaderboard for SEA Languages data docs64.3%
18Gemma 3 27B IT· SeaLLMs Leaderboard for SEA Languages data docs63.9%
19Gemma 3 27B Pt· SeaLLMs Leaderboard for SEA Languages data docs63.4%
20Qwen 2.5 14B Instruct· SeaLLMs Leaderboard for SEA Languages data docs62.7%
21Llama 3.1 70B Instruct· SeaLLMs Leaderboard for SEA Languages data docs60.4%
22Meta Llama 3 70b· SeaLLMs Leaderboard for SEA Languages data docs60.1%
23GPT-4o mini· SeaLLMs Leaderboard for SEA Languages data docs59.2%
24Llama 3.1 70B· SeaLLMs Leaderboard for SEA Languages data docs59.2%
25Llama 3 70B Instruct· SeaLLMs Leaderboard for SEA Languages data docs59%
26Gemma 2 27B IT· SeaLLMs Leaderboard for SEA Languages data docs58%
27Claude Haiku 3.5· SeaLLMs Leaderboard for SEA Languages data docs57.6%
28Gemma 3 12B IT· SeaLLMs Leaderboard for SEA Languages data docs57.6%
29Qwen2.5 7B Instruct· SeaLLMs Leaderboard for SEA Languages data docs57.6%
30Llama 4 Scout· SeaLLMs Leaderboard for SEA Languages data docs56.9%
31Qwen2.5 7B· SeaLLMs Leaderboard for SEA Languages data docs55.9%
32Gemma 2 9B IT· SeaLLMs Leaderboard for SEA Languages data docs54.5%
33gemma2-27b· SeaLLMs Leaderboard for SEA Languages data docs53.8%
34Qwen2 7B Instruct· SeaLLMs Leaderboard for SEA Languages data docs53.4%
35GPT-4.1 nano· SeaLLMs Leaderboard for SEA Languages data docs51.5%
36Qwen2.5 3B Instruct· SeaLLMs Leaderboard for SEA Languages data docs50.3%
37Claude 3 Haiku· SeaLLMs Leaderboard for SEA Languages data docs49.2%
38gemma-2-9b· SeaLLMs Leaderboard for SEA Languages data docs48.5%
39GLM-4-9b-chat· SeaLLMs Leaderboard for SEA Languages data docs43.6%
40Llama 3.1 8B· SeaLLMs Leaderboard for SEA Languages data docs42.7%
41Llama 3.1 8B Instruct· SeaLLMs Leaderboard for SEA Languages data docs42.7%
42Meta Llama 3 8b· SeaLLMs Leaderboard for SEA Languages data docs42%
43GLM 4 9B 0414· SeaLLMs Leaderboard for SEA Languages data docs41.7%
44Gemma 3 4B IT· SeaLLMs Leaderboard for SEA Languages data docs41%
45Llama 3 8B Instruct· SeaLLMs Leaderboard for SEA Languages data docs41%
46Mixtral 8X7b V0.1· SeaLLMs Leaderboard for SEA Languages data docs39.9%
47Qwen2.5 1.5B Instruct· SeaLLMs Leaderboard for SEA Languages data docs39.6%
48Llama 3.2 3B· SeaLLMs Leaderboard for SEA Languages data docs38.5%
49Gemma 2 2B IT· SeaLLMs Leaderboard for SEA Languages data docs38%
50Mixtral 8x7B Instruct v0.1· SeaLLMs Leaderboard for SEA Languages data docs38%

Showing 1–50 of 57 results.

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