SEA-HELM (Indonesian) - syntax-criteria-prose: 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
1DeepSeek V4 ProReasoning85.59#201
2GLM-5.3Reasoning84.1#79
3Qwen-SEA-LION-v5-397B-A17B-PlusReasoning82.37#178
4Gemma 4 26B A4B (IT)Reasoning82.36#563
5Qwen3.8-Flash-NextReasoning82.23#122
6Qwen-SEA-LION-v5-27BReasoning82.14
7Gemma 4 31B (IT)Reasoning81.43#354
8DeepSeek V4 Flash (0731)Reasoning81.42#159
9Inkling-NVFP4Reasoning81.39#235
10DeepSeek V4 FlashReasoning80.21#273
11GLM-5.2 FP8Reasoning79.5#303
12Qwen 3.5 397B A17BReasoning76.41#270
13Qwen 3.5 122B A10BReasoning73.87#350
14Qwen 3.8 27BReasoning72.84#232
15Gemma 4 12B (IT)Reasoning71.5#732

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-syntax-criteria-prose · How It Works · Data refreshed daily, snapshot 2026-11-22.