SEA-HELM (English) - AA-LCR: leaderboard
Artificial Analysis Long Context Reasoning (AA-LCR) questions over long documents, run by SEA-HELM. Normalized 0-100 score from AI Singapore's SEA-HELM leaderboard: (score - random baseline) / (maximum - baseline), floored at 0 and averaged over eight runs; higher is better.
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Around February 2027. 58 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B (Reasoning) | 69.05 | #182 (Qwen 3.6 27B) |
| 2 | Qwen 3.5 122B A10B (Reasoning) | 68.97 | #184 (Qwen 3.5 122B A10B) |
| 3 | Qwen 3.5 27B (Reasoning) | 68.7 | #192 (Qwen 3.5 27B) |
| 4 | Qwen 3.5 35B A3B (Reasoning) | 67.14 | #268 (Qwen 3.5 35B A3B) |
| 5 | Qwen 3.5 9B (Reasoning) | 64.65 | #391 (Qwen 3.5 9B) |
| 6 | Qwen 3.5 4B (Reasoning) | 63.08 | #514 (Qwen 3.5 4B) |
| 7 | Qwen 3.6 35B A3B (Reasoning) | 62.64 | #238 (Qwen 3.6 35B A3B) |
| 8 | Gemma 4 26B A4B (IT) (Reasoning) | 60.95 | #293 (Gemma 4 26B A4B (IT)) |
| 9 | GPT-OSS-120B (Reasoning) | 44.66 | #346 (GPT-OSS-120B) |
| 10 | GLM-4.7 Flash (Reasoning) | 43.26 | #543 (GLM-4.7 Flash) |
| 11 | Qwen 3 VL 32B Instruct | 31.62 | #290 |
| 12 | Llama 4 Scout Instruct | 27.92 | #547 |
| 13 | Mistral Small 4 | 18 | #522 |
| 14 | Llama-SEA-LION-v3-70B-IT | 14.38 | #407 |
| 15 | Qwen 3 VL 4B Instruct | 13.81 | #510 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-english-aa-lcr · How It Works · Data refreshed daily, snapshot 2026-11-05.