SuperCLUE General (November 2026) - Long Context: leaderboard

SuperCLUE’s November 2026 general evaluation. The native 超长上下文 column evaluates very long context. The workbook does not publish a token-window size or per-item scoring protocol here. Source workbook: https://www.superclueai.com/data/generalboard/2026%E5%B9%B411%E6%9C%88.xlsx. The publisher-reported score and exact native model/run labels are retained; higher is better. This question-set edition remains separate from earlier editions.

Metric: Score. Source: www.superclueai.com. Saturation forecast: Around February 2028. 19 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemini 4 Argon95.63#12
2GPT-6.1 Sol88.14#10
3Kimi K3.1 Pro87.25#29
4GLM-5.377.6#68
5DeepSeek V4.1 Flash (1017)66.25#41
6GLM-5.3 Flash57.61#125
7MiniMax-M3.1-Flash51.86#109
8Step 5 Preview49.39#110
9Hy4 preview47.87#71
10Qwen 3.8 Max (0902)44.38#49
11MiniMax-M342.88#272
12LongCat-2.5-Preview42.14
13Qwen 3.8 Flash40.68#119
14Doubao-Seed-2.1-Pro-26091537.68
15MiMo-V2.6-Pro36.83#76

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=superclue-general-november-2026-long-context · How It Works · Data refreshed daily, snapshot 2026-11-16.