SuperCLUE-LongContext - 1M Overall: leaderboard
Metric: Score. Source: www.superclueai.com. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (High) | 91.98 |
| 2 | Gemini 3.1 Pro (Preview) (High) | 73.17 |
| 3 | DeepSeek V4 Pro (Max) | 64.67 |
| 4 | Kimi K3 (Max) | 62.76 |
| 5 | GLM-5.2 (Max) | 47.71 |
| 6 | MiMo-V2.5-Pro | 40.21 |
| 7 | MiniMax-M3 | 24.67 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-longcontext-1m-overall · How It Works · Data refreshed daily, snapshot 2026-09-05.