SEA-HELM (Indonesian) - kopi-sea-indonesia: leaderboard

Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Around February 2027. 75 models tracked. Updated 22 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Inkling-NVFP4Reasoning84.76#235
2GLM-5.3Reasoning84.15#79
3DeepSeek V4 ProReasoning83.57#201
4GLM-5.2 FP8Reasoning80.34#303
5DeepSeek V4 Flash (0731)Reasoning78.28#159
6GLM-4.7Reasoning78.22#383
7Qwen3.8-Flash-NextReasoning77.23#122
8Qwen-SEA-LION-v5-397B-A17B-PlusReasoning75.79#178
9Qwen 3.5 397B A17BReasoning75.56#270
10Gemma 4 31B (IT)Reasoning71.44#354
11DeepSeek V4 FlashReasoning70.61#273
12Inkling SmallReasoning68.69#322
13MiniMax-M3Reasoning67.78#290
14Qwen 3.5 122B A10BReasoning66.66#350
15Nemotron 3.5 Super VL (BF16)Reasoning66.5#371

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=sea-helm-indonesian-kopi-sea-indonesia · How It Works · Data refreshed daily, snapshot 2026-11-22.