SEA-HELM (English) - automationbench: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Around February 2027. 61 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GLM-5.3 | Reasoning | 49.34 | #79 |
| 2 | Qwen3.8-Flash-Next | Reasoning | 48.76 | #122 |
| 3 | Qwen-SEA-LION-v5-27B | Reasoning | 38.61 | |
| 4 | Qwen 3.8 27B | Reasoning | 38.1 | #232 |
| 5 | DeepSeek V4 Flash (0731) | Reasoning | 37.47 | #159 |
| 6 | DeepSeek V4 Flash | Reasoning | 14.87 | #273 |
| 7 | Qwen 3.6 27B | Reasoning | 14.66 | #358 |
| 8 | Gemma 4 26B A4B (IT) | Reasoning | 14.22 | #563 |
| 9 | Gemma 4 31B (IT) | Reasoning | 14 | #354 |
| 10 | Muse Glimmer 30B | Reasoning | 13.66 | #395 |
| 11 | Qwen-SEA-LION-v5-397B-A17B-Plus | Reasoning | 13.27 | #178 |
| 12 | Mistral-Medium-3.5-128B | Reasoning | 11.46 | |
| 13 | Qwen-SEA-LION-v4.5-27B-IT | Reasoning | 10.49 | #538 |
| 14 | Qwen 3.6 35B A3B | Reasoning | 9.73 | #485 |
| 15 | Gemma 4 12B (IT) | Reasoning | 9.19 | #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-english-automationbench · How It Works · Data refreshed daily, snapshot 2026-11-22.