Kaggle Cipher Frontlines: leaderboard
Community benchmark on Kaggle by hanifnoerrofiq: 11 classical ciphers set inside short stories (Caesar, Vigenere, rail fence, affine, Bifid, scytale, Baconian, four-square, ADFGX, a plugboard plus Atbash, Enigma) that the model decodes from the narrative clues. A task passes when the expected plaintext appears in the letters of the reply; percent of ciphers solved, higher is better.
Metric: Ciphers Solved (%). Source: www.kaggle.com. Saturation forecast: Around February 2027. 46 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 100 | #7 |
| 2 | Gemini 3.1 Pro (Preview) | 90.91 | #64 |
| 3 | GPT-5.5 | 90.91 | #33 |
| 4 | Gemini 3 Flash (Preview) | 90.91 | #90 |
| 5 | Gemini 3.5 Flash | 90.91 | #66 |
| 6 | Gemini 3.8 Flash | 90.91 | #30 |
| 7 | GPT-6 Astra | 90.91 | #6 |
| 8 | GPT-5.6 Terra | 90.91 | #40 |
| 9 | Gemini 3.6 Flash | 90.91 | #57 |
| 10 | Gemini 3.7 Flash | 90.91 | #24 |
| 11 | GPT-6 Sol | 90.91 | #19 |
| 12 | Gemini 2.5 Pro | 81.82 | #159 |
| 13 | Claude Opus 4.7 | 81.82 | #51 |
| 14 | GPT-5.6 Sol | 81.82 | #22 |
| 15 | GLM-5 | 81.82 | #149 |
No result here: #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=kaggle-cipher-frontlines · How It Works · Data refreshed daily, snapshot 2026-11-05.