{ "generated": "2026-04-27", "version": "0.2", "description": "Cipher Corpus benchmark baseline statistics for solver evaluation", "corpus_url": "https://ciphermuseum.com/cipher-corpus.html", "citation": { "cipher_corpus": { "title": "Cipher Corpus: Comprehensive Classical Cryptanalysis Benchmark", "author": "Lester, Paul", "year": 2026, "url": "https://ciphermuseum.com/cipher-corpus.html", "note": "17,435+ test cases across 81+ cipher algorithms" }, "related_work": { "title": "CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges", "authors": "Li et al.", "year": 2025, "url": "https://arxiv.org/pdf/2504.19093", "note": "Foundational benchmark establishing LLM cryptanalysis evaluation methodology" } }, "summary": { "total_records": 100026, "verified_records": 99542, "cipher_types": 82, "cipher_families": 13, "languages": [ "en", "fr", "de", "la", "es", "it", "ja", "ru", "zh" ], "public_split": 69922, "blind_split": 30104, "clean_records": 99540, "noisy_records": 486, "historical_records": 54, "difficulty_distribution": { "beginner": 17007, "intermediate": 29410, "advanced": 26608, "expert": 27001 }, "language_distribution": { "en": 96371, "fr": 779, "de": 800, "la": 804, "es": 788, "it": 480, "ja": 2, "ru": 1, "zh": 1 } }, "solver_baselines": { "description": "Expected accuracy ranges for different solver types by difficulty tier", "methodology": "Estimated from cryptanalytic complexity, key space size, historical time-to-break, and LLM evaluation data", "baselines": { "beginner": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "intermediate": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "advanced": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "expert": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" } } }, "per_cipher_stats": [ { "cipher_type": "caesar", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 5102, "public_count": 3600, "blind_count": 1502, "avg_normalized_length": 57, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "brute force", "frequency analysis", "frequency analysis (noisy)", "error correction" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 4992, "noisy_count": 110 }, { "cipher_type": "vigenere", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 4979, "public_count": 3443, "blind_count": 1536, "avg_normalized_length": 58, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "Kasiski examination", "index of coincidence", "frequency analysis", "Kasiski examination (noisy)" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 4867, "noisy_count": 112 }, { "cipher_type": "affine", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 4635, "public_count": 3235, "blind_count": 1400, "avg_normalized_length": 60, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "brute force", "frequency analysis", "known plaintext", "algebraic attack" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 4635, "noisy_count": 0 }, { "cipher_type": "monoalphabetic", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 3782, "public_count": 2658, "blind_count": 1124, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "pattern analysis", "known plaintext", "frequency analysis (noisy)" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 3680, "noisy_count": 102 }, { "cipher_type": "columnar_transposition", "cipher_family": "transposition", "difficulty": "intermediate", "record_count": 3490, "public_count": 2405, "blind_count": 1085, "avg_normalized_length": 59, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "multiple anagramming", "probable word", "column reordering", "multiple anagramming (noisy)" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 3381, "noisy_count": 109 }, { "cipher_type": "playfair", "cipher_family": "polygraphic", "difficulty": "intermediate", "record_count": 3036, "public_count": 2122, "blind_count": 914, "avg_normalized_length": 55, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "bigram frequency analysis", "probable word", "digraph analysis", "bigram frequency analysis (noisy)" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 2985, "noisy_count": 51 }, { "cipher_type": "beaufort", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 2815, "public_count": 1930, "blind_count": 885, "avg_normalized_length": 59, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "Kasiski examination", "index of coincidence", "reciprocal property" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 2815, "noisy_count": 0 }, { "cipher_type": "enigma", "cipher_family": "machine", "difficulty": "expert", "record_count": 2723, "public_count": 1899, "blind_count": 824, "avg_normalized_length": 62, "languages": [ "en", "de" ], "expected_attacks": [ "bombe attack", "known plaintext", "cribs", "index of coincidence" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 2723, "noisy_count": 0 }, { "cipher_type": "gronsfeld", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 2538, "public_count": 1768, "blind_count": 770, "avg_normalized_length": 63, "languages": [ "en" ], "expected_attacks": [ "Kasiski examination", "frequency analysis", "numeric key recovery" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 2538, "noisy_count": 0 }, { "cipher_type": "alberti_disk", "cipher_family": "disk", "difficulty": "expert", "record_count": 2141, "public_count": 1516, "blind_count": 625, "avg_normalized_length": 63, "languages": [ "en", "la" ], "expected_attacks": [ "disk alignment analysis", "probable word", "frequency analysis", "disk cryptanalysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 2141, "noisy_count": 0 }, { "cipher_type": "rail_fence", "cipher_family": "transposition", "difficulty": "intermediate", "record_count": 2125, "public_count": 1496, "blind_count": 629, "avg_normalized_length": 56, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "brute force rails", "pattern analysis", "wave pattern" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 2125, "noisy_count": 0 }, { "cipher_type": "bazeries", "cipher_family": "transposition", "difficulty": "advanced", "record_count": 1970, "public_count": 1362, "blind_count": 608, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "transposition recovery", "frequency analysis", "Bazeries method" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1970, "noisy_count": 0 }, { "cipher_type": "autokey", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 1910, "public_count": 1356, "blind_count": 554, "avg_normalized_length": 58, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "probable word attack", "Kasiski variant", "self-key recovery", "index of coincidence" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1910, "noisy_count": 0 }, { "cipher_type": "scytale", "cipher_family": "transposition", "difficulty": "intermediate", "record_count": 1860, "public_count": 1255, "blind_count": 605, "avg_normalized_length": 65, "languages": [ "en" ], "expected_attacks": [ "brute force diameter", "transposition analysis" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1860, "noisy_count": 0 }, { "cipher_type": "bifid", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1853, "public_count": 1272, "blind_count": 581, "avg_normalized_length": 54, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "bigram frequency analysis", "probable word", "Polybius square recovery", "Polybius recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1853, "noisy_count": 0 }, { "cipher_type": "confederate_vigenere", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 1682, "public_count": 1186, "blind_count": 496, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "Kasiski examination", "disk alignment analysis", "index of coincidence", "probable word" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1682, "noisy_count": 0 }, { "cipher_type": "diana", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 1681, "public_count": 1146, "blind_count": 535, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "Beaufort analysis", "reciprocal property", "frequency analysis", "index of coincidence" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1681, "noisy_count": 0 }, { "cipher_type": "porta", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 1680, "public_count": 1139, "blind_count": 541, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "reciprocal properties", "index of coincidence", "frequency analysis" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1680, "noisy_count": 0 }, { "cipher_type": "adfgx", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1552, "public_count": 1067, "blind_count": 485, "avg_normalized_length": 113, "languages": [ "en" ], "expected_attacks": [ "bigram analysis", "columnar transposition recovery", "Polybius recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1552, "noisy_count": 0 }, { "cipher_type": "trifid", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1530, "public_count": 1090, "blind_count": 440, "avg_normalized_length": 59, "languages": [ "en" ], "expected_attacks": [ "trigram frequency analysis", "probable word", "3D Polybius recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1530, "noisy_count": 0 }, { "cipher_type": "fractionated_morse", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1450, "public_count": 1003, "blind_count": 447, "avg_normalized_length": 71, "languages": [ "en" ], "expected_attacks": [ "Morse code analysis", "trigram frequency", "probable word" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1450, "noisy_count": 0 }, { "cipher_type": "hill", "cipher_family": "polygraphic", "difficulty": "advanced", "record_count": 1450, "public_count": 1040, "blind_count": 410, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "known plaintext", "matrix analysis", "modular arithmetic" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1450, "noisy_count": 0 }, { "cipher_type": "adfgvx", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1391, "public_count": 951, "blind_count": 440, "avg_normalized_length": 123, "languages": [ "en", "de" ], "expected_attacks": [ "hexadecimal frequency", "columnar recovery", "superimposition", "Polybius recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1391, "noisy_count": 0 }, { "cipher_type": "chaocipher", "cipher_family": "machine", "difficulty": "advanced", "record_count": 1391, "public_count": 956, "blind_count": 435, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "statistical analysis", "probable word", "dual-disk recovery", "algorithmic reconstruction" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1391, "noisy_count": 0 }, { "cipher_type": "double_transposition", "cipher_family": "transposition", "difficulty": "advanced", "record_count": 1390, "public_count": 990, "blind_count": 400, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "multiple anagramming", "probable word", "transposition analysis" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1390, "noisy_count": 0 }, { "cipher_type": "lorenz", "cipher_family": "machine", "difficulty": "expert", "record_count": 1301, "public_count": 908, "blind_count": 393, "avg_normalized_length": 58, "languages": [ "en", "de" ], "expected_attacks": [ "statistical analysis", "Colossus methods", "Tutte reconstruction", "wheel pattern analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1301, "noisy_count": 0 }, { "cipher_type": "four_square", "cipher_family": "polygraphic", "difficulty": "advanced", "record_count": 1284, "public_count": 883, "blind_count": 401, "avg_normalized_length": 57, "languages": [ "en" ], "expected_attacks": [ "bigram frequency analysis", "probable word", "four-square structure" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1284, "noisy_count": 0 }, { "cipher_type": "stager_route", "cipher_family": "transposition", "difficulty": "expert", "record_count": 1282, "public_count": 896, "blind_count": 386, "avg_normalized_length": 63, "languages": [ "en" ], "expected_attacks": [ "multiple anagramming", "probable word", "route reconstruction", "route analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1282, "noisy_count": 0 }, { "cipher_type": "m209", "cipher_family": "machine", "difficulty": "expert", "record_count": 1221, "public_count": 888, "blind_count": 333, "avg_normalized_length": 60, "languages": [ "en" ], "expected_attacks": [ "probable word", "wheel recovery", "pin-and-lug analysis", "known plaintext attack" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1221, "noisy_count": 0 }, { "cipher_type": "kryptos", "cipher_family": "polyalphabetic", "difficulty": "advanced", "record_count": 1162, "public_count": 821, "blind_count": 341, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "Kasiski examination", "frequency analysis", "known plaintext", "Vigenere attack" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1162, "noisy_count": 0 }, { "cipher_type": "sigaba", "cipher_family": "machine", "difficulty": "expert", "record_count": 1161, "public_count": 826, "blind_count": 335, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "statistical analysis", "pseudo-random analysis", "never broken", "rotor analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1161, "noisy_count": 0 }, { "cipher_type": "fialka", "cipher_family": "machine", "difficulty": "expert", "record_count": 1161, "public_count": 781, "blind_count": 380, "avg_normalized_length": 61, "languages": [ "en", "ru" ], "expected_attacks": [ "statistical analysis", "multi-rotor recovery", "Soviet methods", "rotor analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1161, "noisy_count": 0 }, { "cipher_type": "kl7", "cipher_family": "machine", "difficulty": "expert", "record_count": 1161, "public_count": 800, "blind_count": 361, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "statistical analysis", "notch wheel recovery", "TSEC methods", "rotor analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1161, "noisy_count": 0 }, { "cipher_type": "geheimschreiber", "cipher_family": "machine", "difficulty": "expert", "record_count": 1161, "public_count": 814, "blind_count": 347, "avg_normalized_length": 61, "languages": [ "en", "de" ], "expected_attacks": [ "wheel pattern analysis", "T52 Sturgeon methods", "XOR analysis", "statistical attack" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1161, "noisy_count": 0 }, { "cipher_type": "kama_sutra", "cipher_family": "substitution", "difficulty": "intermediate", "record_count": 1160, "public_count": 817, "blind_count": 343, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "paired substitution analysis" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 1160, "noisy_count": 0 }, { "cipher_type": "cardano_autokey", "cipher_family": "polyalphabetic", "difficulty": "advanced", "record_count": 1160, "public_count": 821, "blind_count": 339, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "probable word", "autokey recovery", "frequency analysis" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1160, "noisy_count": 0 }, { "cipher_type": "red_type_a", "cipher_family": "machine", "difficulty": "advanced", "record_count": 1160, "public_count": 828, "blind_count": 332, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "vowel/consonant separation", "frequency analysis", "stepping switch" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1160, "noisy_count": 0 }, { "cipher_type": "typex", "cipher_family": "machine", "difficulty": "expert", "record_count": 1160, "public_count": 837, "blind_count": 323, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "bombe-like attack", "statistical analysis", "Enigma-family methods" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 1160, "noisy_count": 0 }, { "cipher_type": "joseon_yeokhak", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 1100, "public_count": 753, "blind_count": 347, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "shift analysis" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 1100, "noisy_count": 0 }, { "cipher_type": "vic", "cipher_family": "substitution", "difficulty": "advanced", "record_count": 1074, "public_count": 742, "blind_count": 332, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "Polybius recovery", "Soviet VIC methods", "checkerboard recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1074, "noisy_count": 0 }, { "cipher_type": "nihilist", "cipher_family": "fractionation", "difficulty": "advanced", "record_count": 1072, "public_count": 781, "blind_count": 291, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "Kasiski variant", "index of coincidence", "additive recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1072, "noisy_count": 0 }, { "cipher_type": "two_square", "cipher_family": "polygraphic", "difficulty": "advanced", "record_count": 1072, "public_count": 754, "blind_count": 318, "avg_normalized_length": 56, "languages": [ "en" ], "expected_attacks": [ "bigram frequency analysis", "probable word" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1072, "noisy_count": 0 }, { "cipher_type": "geez_monastic", "cipher_family": "substitution", "difficulty": "advanced", "record_count": 930, "public_count": 671, "blind_count": 259, "avg_normalized_length": 60, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "keyed alphabet recovery", "monoalphabetic methods" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 930, "noisy_count": 0 }, { "cipher_type": "purple", "cipher_family": "machine", "difficulty": "expert", "record_count": 872, "public_count": 596, "blind_count": 276, "avg_normalized_length": 61, "languages": [ "en", "ja" ], "expected_attacks": [ "probable word", "stepping switch analysis", "vowel/consonant separation", "switch analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 872, "noisy_count": 0 }, { "cipher_type": "copiale", "cipher_family": "substitution", "difficulty": "advanced", "record_count": 871, "public_count": 621, "blind_count": 250, "avg_normalized_length": 61, "languages": [ "en", "de" ], "expected_attacks": [ "homophonic frequency analysis", "codebook recovery", "symbolic analysis", "symbol frequency analysis" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 871, "noisy_count": 0 }, { "cipher_type": "wheatstone", "cipher_family": "polygraphic", "difficulty": "advanced", "record_count": 871, "public_count": 604, "blind_count": 267, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "bigram analysis", "probable word", "Playfair variant analysis", "disk analysis" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 871, "noisy_count": 0 }, { "cipher_type": "great_cipher", "cipher_family": "nomenclator", "difficulty": "expert", "record_count": 871, "public_count": 620, "blind_count": 251, "avg_normalized_length": 0, "languages": [ "en", "fr" ], "expected_attacks": [ "codebook reconstruction", "frequency analysis", "Bazeries method", "syllabic analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 871, "noisy_count": 0 }, { "cipher_type": "jn25", "cipher_family": "codebook", "difficulty": "expert", "record_count": 871, "public_count": 594, "blind_count": 277, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "additive recovery", "superencipherment analysis", "Pacific COMINT", "codebook reconstruction" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 871, "noisy_count": 0 }, { "cipher_type": "venona_pad_reuse", "cipher_family": "stream", "difficulty": "expert", "record_count": 871, "public_count": 611, "blind_count": 260, "avg_normalized_length": 54, "languages": [ "en" ], "expected_attacks": [ "pad reuse attack", "crib dragging", "XOR analysis", "Venona project" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 871, "noisy_count": 0 }, { "cipher_type": "straddling_checkerboard", "cipher_family": "substitution", "difficulty": "advanced", "record_count": 870, "public_count": 610, "blind_count": 260, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "Polybius recovery", "Soviet methods" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 870, "noisy_count": 0 }, { "cipher_type": "kryha", "cipher_family": "machine", "difficulty": "expert", "record_count": 870, "public_count": 596, "blind_count": 274, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "statistical analysis", "Friedman attack", "index of coincidence" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 870, "noisy_count": 0 }, { "cipher_type": "argenti", "cipher_family": "nomenclator", "difficulty": "expert", "record_count": 870, "public_count": 639, "blind_count": 231, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "codebook recovery", "papal methods" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 870, "noisy_count": 0 }, { "cipher_type": "slidex", "cipher_family": "transposition", "difficulty": "advanced", "record_count": 870, "public_count": 612, "blind_count": 258, "avg_normalized_length": 61, "languages": [ "en" ], "expected_attacks": [ "probable word", "transposition analysis", "slide recovery" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 870, "noisy_count": 0 }, { "cipher_type": "solitaire", "cipher_family": "stream", "difficulty": "expert", "record_count": 811, "public_count": 571, "blind_count": 240, "avg_normalized_length": 62, "languages": [ "en" ], "expected_attacks": [ "card deck reconstruction", "Pontifex cryptanalysis", "card deck analysis", "keystream recovery" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 811, "noisy_count": 0 }, { "cipher_type": "chinese_telegraph", "cipher_family": "codebook", "difficulty": "expert", "record_count": 811, "public_count": 562, "blind_count": 249, "avg_normalized_length": 0, "languages": [ "en", "zh" ], "expected_attacks": [ "codebook reconstruction", "numeric frequency analysis", "frequency analysis", "context-based attack" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 811, "noisy_count": 0 }, { "cipher_type": "nomenclator", "cipher_family": "nomenclator", "difficulty": "expert", "record_count": 810, "public_count": 582, "blind_count": 228, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "frequency analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 810, "noisy_count": 0 }, { "cipher_type": "m94", "cipher_family": "machine", "difficulty": "expert", "record_count": 772, "public_count": 513, "blind_count": 259, "avg_normalized_length": 48, "languages": [ "en" ], "expected_attacks": [ "multiple anagramming", "disk recovery", "probable word", "column analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 772, "noisy_count": 0 }, { "cipher_type": "jefferson_disk", "cipher_family": "disk", "difficulty": "expert", "record_count": 757, "public_count": 522, "blind_count": 235, "avg_normalized_length": 46, "languages": [ "en" ], "expected_attacks": [ "multiple anagramming", "probable word", "disk alignment", "column analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 757, "noisy_count": 0 }, { "cipher_type": "wallis_cipher", "cipher_family": "nomenclator", "difficulty": "expert", "record_count": 580, "public_count": 411, "blind_count": 169, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "frequency analysis", "Wallis methods" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 580, "noisy_count": 0 }, { "cipher_type": "one_time_pad", "cipher_family": "stream", "difficulty": "expert", "record_count": 485, "public_count": 336, "blind_count": 149, "avg_normalized_length": 44, "languages": [ "en" ], "expected_attacks": [ "perfect secrecy — unbreakable with true OTP", "pad reuse attack", "perfect secrecy" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 485, "noisy_count": 0 }, { "cipher_type": "vernam", "cipher_family": "stream", "difficulty": "expert", "record_count": 485, "public_count": 333, "blind_count": 152, "avg_normalized_length": 44, "languages": [ "en" ], "expected_attacks": [ "XOR-based pad recovery", "pad reuse attack" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 485, "noisy_count": 0 }, { "cipher_type": "rot13", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 405, "public_count": 305, "blind_count": 100, "avg_normalized_length": 52, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "ROT13 is self-inverse", "trivial decryption", "frequency analysis", "brute force" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 405, "noisy_count": 0 }, { "cipher_type": "atbash", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 405, "public_count": 283, "blind_count": 122, "avg_normalized_length": 52, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "reflection property", "known encoding", "frequency analysis" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 405, "noisy_count": 0 }, { "cipher_type": "polybius", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 378, "public_count": 274, "blind_count": 104, "avg_normalized_length": 0, "languages": [ "en", "fr", "de", "la", "es", "it" ], "expected_attacks": [ "frequency analysis", "bigram analysis", "known encoding", "known encoding scheme" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 378, "noisy_count": 0 }, { "cipher_type": "trithemius", "cipher_family": "polyalphabetic", "difficulty": "beginner", "record_count": 350, "public_count": 252, "blind_count": 98, "avg_normalized_length": 58, "languages": [ "en" ], "expected_attacks": [ "known plaintext", "progressive shift analysis" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 350, "noisy_count": 0 }, { "cipher_type": "running_key", "cipher_family": "polyalphabetic", "difficulty": "intermediate", "record_count": 348, "public_count": 247, "blind_count": 101, "avg_normalized_length": 17, "languages": [ "en" ], "expected_attacks": [ "probable word attack", "running key alignment" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 348, "noisy_count": 0 }, { "cipher_type": "zimmermann", "cipher_family": "codebook", "difficulty": "expert", "record_count": 292, "public_count": 219, "blind_count": 73, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "diplomatic code analysis", "Room 40 methods", "traffic analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 292, "noisy_count": 0 }, { "cipher_type": "culper_ring", "cipher_family": "codebook", "difficulty": "expert", "record_count": 292, "public_count": 203, "blind_count": 89, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "numeric analysis", "American Revolution", "frequency analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 292, "noisy_count": 0 }, { "cipher_type": "morse_code", "cipher_family": "encoding", "difficulty": "beginner", "record_count": 290, "public_count": 214, "blind_count": 76, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "known encoding scheme", "symbol frequency" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 290, "noisy_count": 0 }, { "cipher_type": "commercial_code", "cipher_family": "codebook", "difficulty": "expert", "record_count": 290, "public_count": 197, "blind_count": 93, "avg_normalized_length": 342, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "word frequency analysis", "telegraph era" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 290, "noisy_count": 0 }, { "cipher_type": "pigpen", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 252, "public_count": 178, "blind_count": 74, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "symbol frequency analysis", "known encoding", "pattern matching" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 252, "noisy_count": 0 }, { "cipher_type": "voynich_render", "cipher_family": "substitution", "difficulty": "expert", "record_count": 252, "public_count": 175, "blind_count": 77, "avg_normalized_length": 46, "languages": [ "en" ], "expected_attacks": [ "symbol frequency analysis", "glyph substitution", "linguistic analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 252, "noisy_count": 0 }, { "cipher_type": "babington", "cipher_family": "nomenclator", "difficulty": "expert", "record_count": 249, "public_count": 174, "blind_count": 75, "avg_normalized_length": 23, "languages": [ "en" ], "expected_attacks": [ "codebook reconstruction", "frequency analysis", "Walsingham methods", "nomenclator reconstruction" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 249, "noisy_count": 1 }, { "cipher_type": "null_cipher", "cipher_family": "steganography", "difficulty": "advanced", "record_count": 234, "public_count": 176, "blind_count": 58, "avg_normalized_length": 65, "languages": [ "en", "fr" ], "expected_attacks": [ "letter position extraction", "statistical analysis", "carrier detection", "word selection pattern" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 234, "noisy_count": 0 }, { "cipher_type": "tap_code", "cipher_family": "substitution", "difficulty": "beginner", "record_count": 192, "public_count": 138, "blind_count": 54, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "known encoding scheme", "frequency analysis" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 192, "noisy_count": 0 }, { "cipher_type": "navajo_code", "cipher_family": "code", "difficulty": "expert", "record_count": 119, "public_count": 84, "blind_count": 35, "avg_normalized_length": 93, "languages": [ "en" ], "expected_attacks": [ "reverse dictionary lookup", "phonetic analysis", "word frequency", "linguistic analysis" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 119, "noisy_count": 0 }, { "cipher_type": "arnold_andre", "cipher_family": "codebook", "difficulty": "expert", "record_count": 117, "public_count": 81, "blind_count": 36, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "book identification", "word frequency analysis", "West Point treason", "codebook reconstruction" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 117, "noisy_count": 0 }, { "cipher_type": "bacon_cipher", "cipher_family": "steganography", "difficulty": "beginner", "record_count": 116, "public_count": 79, "blind_count": 37, "avg_normalized_length": 83, "languages": [ "en" ], "expected_attacks": [ "known encoding scheme", "pattern recognition" ], "solver_baselines": { "human": "95-100%", "automated": "95-100%", "llm_3shot": "80-95%", "llm_0shot": "60-80%" }, "verified_count": 116, "noisy_count": 0 }, { "cipher_type": "aeneas_tacticus", "cipher_family": "steganography", "difficulty": "expert", "record_count": 116, "public_count": 79, "blind_count": 37, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "numeric position analysis", "known encoding" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 116, "noisy_count": 0 }, { "cipher_type": "homophonic", "cipher_family": "substitution", "difficulty": "intermediate", "record_count": 107, "public_count": 76, "blind_count": 31, "avg_normalized_length": 0, "languages": [ "en" ], "expected_attacks": [ "frequency analysis (harder)", "pattern analysis", "homophone grouping", "frequency analysis" ], "solver_baselines": { "human": "60-90%", "automated": "60-90%", "llm_3shot": "40-70%", "llm_0shot": "20-50%" }, "verified_count": 107, "noisy_count": 0 }, { "cipher_type": "book_cipher", "cipher_family": "codebook", "difficulty": "expert", "record_count": 65, "public_count": 48, "blind_count": 17, "avg_normalized_length": 1, "languages": [ "en" ], "expected_attacks": [ "book identification", "word frequency analysis", "probable word", "Declaration of Independence mapping" ], "solver_baselines": { "human": "5-30%", "automated": "5-30%", "llm_3shot": "2-15%", "llm_0shot": "1-5%" }, "verified_count": 65, "noisy_count": 1 }, { "cipher_type": "wallis_ciphers", "cipher_family": "polyalphabetic", "difficulty": "advanced", "record_count": 1, "public_count": 1, "blind_count": 0, "avg_normalized_length": 20, "languages": [ "en" ], "expected_attacks": [ "frequency analysis", "bigram analysis", "index of coincidence" ], "solver_baselines": { "human": "20-60%", "automated": "20-60%", "llm_3shot": "10-40%", "llm_0shot": "5-20%" }, "verified_count": 1, "noisy_count": 0 } ], "per_family_stats": [ { "family": "substitution", "record_count": 21896, "cipher_types": [ "caesar", "rot13", "atbash", "monoalphabetic", "affine", "polybius", "tap_code", "joseon_yeokhak", "homophonic", "kama_sutra", "straddling_checkerboard", "vic", "copiale", "geez_monastic", "pigpen", "voynich_render", "playfair", "babington", "null_cipher", "chaocipher" ], "difficulty_distribution": { "beginner": 16251, "intermediate": 1643, "advanced": 3746, "expert": 256 } }, { "family": "polyalphabetic", "record_count": 20307, "cipher_types": [ "trithemius", "vigenere", "beaufort", "gronsfeld", "porta", "running_key", "autokey", "confederate_vigenere", "diana", "kryptos", "cardano_autokey", "alberti_disk", "wallis_ciphers", "wheatstone" ], "difficulty_distribution": { "beginner": 350, "intermediate": 17631, "advanced": 2325, "expert": 1 } }, { "family": "machine", "record_count": 16114, "cipher_types": [ "chaocipher", "red_type_a", "enigma", "lorenz", "sigaba", "typex", "m209", "purple", "fialka", "kl7", "geheimschreiber", "kryha", "m94", "jefferson_disk" ], "difficulty_distribution": { "advanced": 2550, "expert": 13564 } }, { "family": "transposition", "record_count": 12988, "cipher_types": [ "rail_fence", "columnar_transposition", "scytale", "double_transposition", "bazeries", "stager_route", "slidex", "kryptos" ], "difficulty_distribution": { "intermediate": 7476, "advanced": 4231, "expert": 1281 } }, { "family": "fractionation", "record_count": 8848, "cipher_types": [ "bifid", "trifid", "adfgx", "adfgvx", "nihilist", "fractionated_morse" ], "difficulty_distribution": { "advanced": 8848 } }, { "family": "polygraphic", "record_count": 7336, "cipher_types": [ "playfair", "four_square", "two_square", "hill", "wheatstone" ], "difficulty_distribution": { "intermediate": 2660, "advanced": 4676 } }, { "family": "nomenclator", "record_count": 3377, "cipher_types": [ "great_cipher", "babington", "nomenclator", "argenti", "wallis_cipher" ], "difficulty_distribution": { "expert": 3377 } }, { "family": "disk", "record_count": 2896, "cipher_types": [ "jefferson_disk", "alberti_disk" ], "difficulty_distribution": { "expert": 2896 } }, { "family": "codebook", "record_count": 2741, "cipher_types": [ "book_cipher", "chinese_telegraph", "zimmermann", "culper_ring", "arnold_andre", "commercial_code", "jn25", "great_cipher", "navajo_code" ], "difficulty_distribution": { "expert": 2741 } }, { "family": "stream", "record_count": 2652, "cipher_types": [ "solitaire", "venona_pad_reuse", "one_time_pad", "vernam" ], "difficulty_distribution": { "expert": 2652 } }, { "family": "steganography", "record_count": 464, "cipher_types": [ "bacon_cipher", "null_cipher", "aeneas_tacticus" ], "difficulty_distribution": { "beginner": 116, "advanced": 232, "expert": 116 } }, { "family": "encoding", "record_count": 290, "cipher_types": [ "morse_code" ], "difficulty_distribution": { "beginner": 290 } }, { "family": "code", "record_count": 117, "cipher_types": [ "navajo_code" ], "difficulty_distribution": { "expert": 117 } } ], "benchmark_splits": { "public": { "count": 69922, "description": "70% of records — available for training and development evaluation", "note": "Do not train and evaluate on the same split" }, "blind": { "count": 30104, "description": "30% of records — held-out for honest evaluation of trained solvers", "note": "Blind split should only be accessed during final evaluation" } }, "comparison_with_cipherbank": { "cipherbank": { "records": 2358, "cipher_types": 9, "historical": false, "live_infrastructure": false, "blind_splits": false }, "cipher_corpus": { "records": 100026, "cipher_types": 82, "historical": 54, "live_infrastructure": true, "blind_splits": true, "multilingual": true }, "note": "Cipher Corpus extends the CipherBank methodology to a broader cipher set with historical records and live benchmark infrastructure." } }