SEA-HELM (Thai) - kopi-sea-thailand: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Around February 2027. 75 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Inkling-NVFP4 | Reasoning | 80.54 | #235 |
| 2 | DeepSeek V4 Pro | Reasoning | 80.16 | #201 |
| 3 | DeepSeek V4 Flash (0731) | Reasoning | 80.07 | #159 |
| 4 | Qwen 3.5 397B A17B | Reasoning | 76.46 | #270 |
| 5 | Qwen-SEA-LION-v5-397B-A17B-Plus | Reasoning | 76.11 | #178 |
| 6 | GLM-4.7 | Reasoning | 73.6 | #383 |
| 7 | Qwen3.8-Flash-Next | Reasoning | 73.12 | #122 |
| 8 | GLM-5.3 | Reasoning | 71.85 | #79 |
| 9 | GLM-5.2 FP8 | Reasoning | 71.28 | #303 |
| 10 | Gemma 4 31B (IT) | Reasoning | 69.23 | #354 |
| 11 | DeepSeek V4 Flash | Reasoning | 68.52 | #273 |
| 12 | Nemotron 3.5 Super VL (BF16) | Reasoning | 67.85 | #371 |
| 13 | Gemma 4 26B A4B (IT) | Reasoning | 62.06 | #563 |
| 14 | Qwen 3.5 122B A10B | Reasoning | 60.37 | #350 |
| 15 | MiniMax-M3 | Reasoning | 59.98 | #290 |
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-thai-kopi-sea-thailand · How It Works · Data refreshed daily, snapshot 2026-11-22.