[ { "name": "Aristotle", "slug": "aristotle", "claims": 198, "primary": 46, "outcomes": { "incorrect": 3, "partial": 24, "full": 169, "candidate": 2 }, "statements": [ "erdos:1000", "erdos:1007", "erdos:1008", "erdos:1022", "erdos:1023", "erdos:1026", "erdos:1028", "erdos:1034", "erdos:1036", "erdos:1037", "erdos:1039", "erdos:1043", "erdos:1044", "erdos:1047", "erdos:1048", "erdos:105", "erdos:106", "erdos:1067", "erdos:1071", "erdos:1080", "erdos:1090", "erdos:1095", "erdos:1098", "erdos:11", "erdos:1102", "erdos:1121", "erdos:1125", "erdos:1126", "erdos:1136", "erdos:1138", "erdos:115", "erdos:1193", "erdos:1197", "erdos:124", "erdos:134", "erdos:150", "erdos:154", "erdos:178", "erdos:189", "erdos:192", "erdos:194", "erdos:198", "erdos:199", "erdos:204", "erdos:205", "erdos:206", "erdos:21", "erdos:214", "erdos:221", "erdos:226", "erdos:229", "erdos:231", "erdos:237", "erdos:24", "erdos:246", "erdos:258", "erdos:259", "erdos:26", "erdos:263", "erdos:264", "erdos:268", "erdos:275", "erdos:280", "erdos:281", "erdos:283", "erdos:290", "erdos:296", "erdos:31", "erdos:314", "erdos:315", "erdos:326", "erdos:331", "erdos:337", "erdos:34", "erdos:345", "erdos:347", "erdos:350", "erdos:353", "erdos:355", "erdos:363", "erdos:367", "erdos:368", "erdos:369", "erdos:370", "erdos:38", "erdos:397", "erdos:401", "erdos:418", "erdos:419", "erdos:425", "erdos:426", "erdos:427", "erdos:429", "erdos:43", "erdos:433", "erdos:434", "erdos:435", "erdos:443", "erdos:447", "erdos:451", "erdos:453", "erdos:457", "erdos:459", "erdos:464", "erdos:476", "erdos:480", "erdos:481", "erdos:484", "erdos:487", "erdos:488", "erdos:490", "erdos:493", "erdos:497", "erdos:498", "erdos:499", "erdos:502", "erdos:503", "erdos:505", "erdos:512", "erdos:519", "erdos:537", "erdos:540", "erdos:541", "erdos:56", "erdos:582", "erdos:598", "erdos:610", "erdos:618", "erdos:621", "erdos:635", "erdos:639", "erdos:645", "erdos:646", "erdos:648", "erdos:649", "erdos:650", "erdos:658", "erdos:659", "erdos:666", "erdos:678", "erdos:679", "erdos:692", "erdos:694", "erdos:696", "erdos:698", "erdos:7", "erdos:71", "erdos:716", "erdos:728", "erdos:729", "erdos:753", "erdos:756", "erdos:760", "erdos:762", "erdos:765", "erdos:775", "erdos:785", "erdos:788", "erdos:794", "erdos:798", "erdos:81", "erdos:818", "erdos:844", "erdos:845", "erdos:848", "erdos:862", "erdos:866", "erdos:867", "erdos:888", "erdos:897", "erdos:898", "erdos:904", "erdos:905", "erdos:907", "erdos:914", "erdos:923", "erdos:927", "erdos:93", "erdos:942", "erdos:947", "erdos:948", "erdos:956", "erdos:958", "erdos:964", "erdos:966", "erdos:967", "erdos:974", "erdos:997" ], "targets": [], "verified": [ "erdos:1007", "erdos:105", "erdos:353", "erdos:464", "erdos:512", "erdos:582", "erdos:760", "erdos:762", "erdos:775" ], "first": "2025-10-25", "last": "2026-06-23", "statement_count": 188, "target_count": 0, "verified_count": 9, "line": "Aristotle", "lab": "Harmonic", "lab_source": "https://www.harmonic.fun/", "catch_all": false }, { "name": "AlphaEvolve", "slug": "alphaevolve", "claims": 79, "primary": 78, "outcomes": { "partial": 6, "unstated": 26, "full": 2, "record": 20, "below": 8, "matched": 12, "superseded": 5 }, "statements": [ "erdos:1026", "erdos:1038", "erdos:1097", "erdos:1132", "erdos:1153", "erdos:36", "erdos:507", "erdos:650", "erdos:951" ], "targets": [ "alphaevolve:1", "alphaevolve:10", "alphaevolve:11", "alphaevolve:12", "alphaevolve:13", "alphaevolve:14", "alphaevolve:15", "alphaevolve:16", "alphaevolve:17", "alphaevolve:18", "alphaevolve:19", "alphaevolve:2", "alphaevolve:20", "alphaevolve:21", "alphaevolve:22", "alphaevolve:23", "alphaevolve:24", "alphaevolve:25", "alphaevolve:26", "alphaevolve:27", "alphaevolve:28", "alphaevolve:29", "alphaevolve:3", "alphaevolve:30", "alphaevolve:31", "alphaevolve:32", "alphaevolve:33", "alphaevolve:34", "alphaevolve:35", "alphaevolve:36", "alphaevolve:37", "alphaevolve:38", "alphaevolve:39", "alphaevolve:4", "alphaevolve:40", "alphaevolve:41", "alphaevolve:42", "alphaevolve:43", "alphaevolve:44", "alphaevolve:45", "alphaevolve:46", "alphaevolve:47", "alphaevolve:48", "alphaevolve:49", "alphaevolve:5", "alphaevolve:50", "alphaevolve:51", "alphaevolve:52", "alphaevolve:53", "alphaevolve:54", "alphaevolve:55", "alphaevolve:56", "alphaevolve:57", "alphaevolve:58", "alphaevolve:59", "alphaevolve:6", "alphaevolve:60", "alphaevolve:61", "alphaevolve:62", "alphaevolve:63", "alphaevolve:64", "alphaevolve:65", "alphaevolve:66", "alphaevolve:67", "alphaevolve:68", "alphaevolve:7", "alphaevolve:8", "alphaevolve:9", "kissing:dimension-11", "matmul:omega" ], "verified": [], "first": "2025-06-16", "last": "2026-08-17", "statement_count": 9, "target_count": 70, "verified_count": 0, "line": "AlphaEvolve", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/", "catch_all": false }, { "name": "GPT-5.5 Pro", "slug": "gpt-5-5-pro", "claims": 73, "primary": 66, "outcomes": { "partial": 21, "candidate": 26, "full": 25, "record": 1 }, "statements": [ "erdos:1004", "erdos:1032", "erdos:1033", "erdos:1039", "erdos:1054", "erdos:1092", "erdos:1101", "erdos:1131", "erdos:1133", "erdos:1138", "erdos:1139", "erdos:1143", "erdos:1148", "erdos:1151", "erdos:1190", "erdos:1194", "erdos:1201", "erdos:1208", "erdos:176", "erdos:202", "erdos:21", "erdos:263", "erdos:283", "erdos:330", "erdos:346", "erdos:351", "erdos:352", "erdos:36", "erdos:38", "erdos:390", "erdos:393", "erdos:42", "erdos:432", "erdos:451", "erdos:456", "erdos:490", "erdos:501", "erdos:503", "erdos:514", "erdos:52", "erdos:521", "erdos:536", "erdos:623", "erdos:671", "erdos:689", "erdos:694", "erdos:696", "erdos:730", "erdos:750", "erdos:81", "erdos:836", "erdos:852", "erdos:865", "erdos:870", "erdos:872", "erdos:875", "erdos:888", "erdos:896", "erdos:90", "erdos:906", "erdos:948", "erdos:953", "erdos:956", "erdos:983" ], "targets": [ "borsuk:dimension" ], "verified": [ "erdos:346", "erdos:689", "erdos:865" ], "first": "2025-10-29", "last": "2026-06-29", "statement_count": 64, "target_count": 1, "verified_count": 3, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT-5.4 Pro", "slug": "gpt-5-4-pro", "claims": 45, "primary": 41, "outcomes": { "partial": 20, "full": 20, "unstated": 1, "incorrect": 1, "candidate": 3 }, "statements": [ "erdos:1062", "erdos:1095", "erdos:1132", "erdos:1141", "erdos:1148", "erdos:1153", "erdos:1183", "erdos:1190", "erdos:1194", "erdos:1195", "erdos:1196", "erdos:1197", "erdos:1202", "erdos:1209", "erdos:1217", "erdos:202", "erdos:25", "erdos:251", "erdos:258", "erdos:342", "erdos:352", "erdos:374", "erdos:380", "erdos:396", "erdos:415", "erdos:503", "erdos:514", "erdos:524", "erdos:574", "erdos:598", "erdos:603", "erdos:610", "erdos:650", "erdos:675", "erdos:75", "erdos:856", "erdos:858", "erdos:863", "erdos:870", "erdos:872", "erdos:943", "erdos:990", "erdos:995", "erdos:996" ], "targets": [], "verified": [], "first": "2026-03-07", "last": "2026-06-21", "statement_count": 44, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT", "slug": "gpt", "claims": 43, "primary": 17, "outcomes": { "incorrect": 1, "full": 29, "partial": 6, "candidate": 7 }, "statements": [ "erdos:1000", "erdos:1021", "erdos:1026", "erdos:1043", "erdos:1061", "erdos:1071", "erdos:1084", "erdos:11", "erdos:1124", "erdos:1151", "erdos:1177", "erdos:154", "erdos:198", "erdos:218", "erdos:31", "erdos:345", "erdos:346", "erdos:347", "erdos:350", "erdos:369", "erdos:370", "erdos:396", "erdos:400", "erdos:418", "erdos:425", "erdos:481", "erdos:493", "erdos:533", "erdos:541", "erdos:550", "erdos:56", "erdos:575", "erdos:593", "erdos:645", "erdos:649", "erdos:672", "erdos:705", "erdos:707", "erdos:731", "erdos:762", "erdos:768", "erdos:947", "erdos:965" ], "targets": [], "verified": [ "erdos:346", "erdos:707", "erdos:762" ], "first": "2025-10-25", "last": "2026-06-27", "statement_count": 43, "target_count": 0, "verified_count": 3, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Codex", "slug": "codex", "claims": 30, "primary": 21, "outcomes": { "partial": 13, "full": 13, "candidate": 3, "superseded": 1 }, "statements": [ "erdos:1032", "erdos:1038", "erdos:1039", "erdos:1070", "erdos:1151", "erdos:1187", "erdos:1194", "erdos:164", "erdos:176", "erdos:224", "erdos:326", "erdos:330", "erdos:346", "erdos:347", "erdos:396", "erdos:399", "erdos:42", "erdos:536", "erdos:539", "erdos:603", "erdos:619", "erdos:671", "erdos:689", "erdos:875", "erdos:94", "erdos:942" ], "targets": [ "primes:bounded-gaps" ], "verified": [ "erdos:346", "erdos:689", "erdos:94" ], "first": "2025-10-25", "last": "2026-09-01", "statement_count": 26, "target_count": 1, "verified_count": 3, "line": "Codex", "lab": "OpenAI", "lab_source": "https://openai.com/codex/", "catch_all": false }, { "name": "GPT-5.2 Pro", "slug": "gpt-5-2-pro", "claims": 30, "primary": 22, "outcomes": { "partial": 8, "incorrect": 5, "full": 15, "unstated": 1, "candidate": 1 }, "statements": [ "erdos:1044", "erdos:1129", "erdos:1130", "erdos:1139", "erdos:1141", "erdos:1148", "erdos:233", "erdos:281", "erdos:333", "erdos:342", "erdos:358", "erdos:397", "erdos:401", "erdos:42", "erdos:457", "erdos:513", "erdos:524", "erdos:543", "erdos:616", "erdos:635", "erdos:652", "erdos:728", "erdos:729", "erdos:788", "erdos:847", "erdos:851", "erdos:872", "erdos:951" ], "targets": [], "verified": [], "first": "2025-12-25", "last": "2026-06-19", "statement_count": 28, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT-5.2 Thinking", "slug": "gpt-5-2-thinking", "claims": 29, "primary": 16, "outcomes": { "full": 14, "partial": 13, "incorrect": 2 }, "statements": [ "erdos:1038", "erdos:1141", "erdos:1147", "erdos:1148", "erdos:1153", "erdos:1154", "erdos:1161", "erdos:205", "erdos:224", "erdos:306", "erdos:349", "erdos:358", "erdos:392", "erdos:423", "erdos:457", "erdos:513", "erdos:543", "erdos:684", "erdos:686", "erdos:728", "erdos:751", "erdos:776", "erdos:783", "erdos:846", "erdos:848", "erdos:888", "erdos:94", "erdos:951" ], "targets": [], "verified": [ "erdos:94" ], "first": "2025-08-09", "last": "2026-03-24", "statement_count": 28, "target_count": 0, "verified_count": 1, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "ChatGPT Deep research", "slug": "chatgpt-deep-research", "claims": 26, "primary": 1, "outcomes": { "partial": 18, "incorrect": 2, "full": 6 }, "statements": [ "erdos:1016", "erdos:1019", "erdos:1099", "erdos:1105", "erdos:1216", "erdos:214", "erdos:325", "erdos:330", "erdos:347", "erdos:354", "erdos:370", "erdos:387", "erdos:397", "erdos:481", "erdos:516", "erdos:559", "erdos:591", "erdos:647", "erdos:650", "erdos:729", "erdos:793", "erdos:851", "erdos:871", "erdos:915", "erdos:942", "erdos:990" ], "targets": [], "verified": [], "first": "2025-10-17", "last": "2026-03-10", "statement_count": 26, "target_count": 0, "verified_count": 0, "line": "ChatGPT", "lab": "OpenAI", "lab_source": "https://openai.com/chatgpt/", "catch_all": false }, { "name": "GPT-5", "slug": "gpt-5", "claims": 24, "primary": 1, "outcomes": { "partial": 10, "full": 14 }, "statements": [ "erdos:1008", "erdos:1011", "erdos:1043", "erdos:1079", "erdos:167", "erdos:188", "erdos:223", "erdos:339", "erdos:35", "erdos:494", "erdos:515", "erdos:621", "erdos:645", "erdos:66", "erdos:737", "erdos:750", "erdos:788", "erdos:811", "erdos:822", "erdos:827", "erdos:829", "erdos:848", "erdos:903", "erdos:94" ], "targets": [], "verified": [ "erdos:94" ], "first": "2025-09-29", "last": "2025-11-20", "statement_count": 24, "target_count": 0, "verified_count": 1, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Claude", "slug": "claude", "claims": 24, "primary": 16, "outcomes": { "partial": 8, "incorrect": 3, "full": 9, "superseded": 2, "record": 2 }, "statements": [ "erdos:1132", "erdos:1153", "erdos:306", "erdos:330", "erdos:388", "erdos:396", "erdos:411", "erdos:43", "erdos:481", "erdos:516", "erdos:686", "erdos:848", "erdos:851", "erdos:931", "erdos:971", "erdos:986", "mathlib:FermatLastTheorem", "pde:BoussinesqSmoothForcingBlowup", "pde:EulerSmoothForcingBlowup", "pde:PorousMediaSmoothForcingBlowup" ], "targets": [ "elliptic:rank-record", "primes:bounded-gaps", "zeta:critical-line-proportion" ], "verified": [ "zeta:critical-line-proportion" ], "first": "2025-08-09", "last": "2026-09-07", "statement_count": 20, "target_count": 3, "verified_count": 1, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "GPT-5.4 Thinking", "slug": "gpt-5-4-thinking", "claims": 19, "primary": 13, "outcomes": { "partial": 13, "full": 4, "candidate": 1, "incorrect": 1 }, "statements": [ "erdos:1038", "erdos:1041", "erdos:1196", "erdos:12", "erdos:120", "erdos:1216", "erdos:138", "erdos:396", "erdos:423", "erdos:602", "erdos:629", "erdos:684", "erdos:686", "erdos:749", "erdos:848", "erdos:873", "erdos:985" ], "targets": [], "verified": [], "first": "2025-08-09", "last": "2026-04-29", "statement_count": 17, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT-5.5", "slug": "gpt-5-5", "claims": 14, "primary": 10, "outcomes": { "partial": 6, "candidate": 3, "full": 5 }, "statements": [ "erdos:1038", "erdos:1039", "erdos:1070", "erdos:1187", "erdos:326", "erdos:327", "erdos:52", "erdos:539", "erdos:603", "erdos:619", "erdos:71", "erdos:819", "erdos:942" ], "targets": [], "verified": [], "first": "2025-12-16", "last": "2026-06-29", "statement_count": 13, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Aletheia", "slug": "aletheia", "claims": 14, "primary": 8, "outcomes": { "partial": 4, "full": 10 }, "statements": [ "erdos:1040", "erdos:1051", "erdos:1089", "erdos:1105", "erdos:333", "erdos:397", "erdos:591", "erdos:652", "erdos:654", "erdos:659", "erdos:705", "erdos:75", "erdos:935", "erdos:992" ], "targets": [], "verified": [], "first": "2026-01-29", "last": "2026-02-02", "statement_count": 14, "target_count": 0, "verified_count": 0, "line": "Aletheia", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/blog/accelerating-mathematical-and-scientific-discovery-with-gemini-deep-think/", "catch_all": false }, { "name": "Gemini Deep Research", "slug": "gemini-deep-research", "claims": 14, "primary": 0, "outcomes": { "partial": 10, "incorrect": 1, "full": 3 }, "statements": [ "erdos:1016", "erdos:1019", "erdos:1099", "erdos:1123", "erdos:1150", "erdos:214", "erdos:330", "erdos:370", "erdos:481", "erdos:516", "erdos:559", "erdos:659", "erdos:851", "erdos:990" ], "targets": [], "verified": [], "first": "2025-10-17", "last": "2026-02-20", "statement_count": 14, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "OpenAI internal model", "slug": "openai-internal-model", "claims": 13, "primary": 13, "outcomes": { "full": 11, "partial": 2 }, "statements": [ "erdos:1014", "erdos:1091", "erdos:1141", "erdos:684", "erdos:741", "erdos:846", "erdos:90", "erdos:960", "erdos:986", "erdos:987", "erdos:990", "erdos:997", "millennium:NavierStokes" ], "targets": [], "verified": [], "first": "2026-02-25", "last": "2026-09-08", "statement_count": 13, "target_count": 0, "verified_count": 0, "line": "OpenAI internal model", "lab": "OpenAI", "lab_source": "https://openai.com/index/navier-stokes-solution/", "catch_all": false }, { "name": "DeepMind prover agent", "slug": "deepmind-prover-agent", "claims": 11, "primary": 11, "outcomes": { "partial": 6, "full": 5 }, "statements": [ "erdos:1082", "erdos:12", "erdos:120", "erdos:125", "erdos:138", "erdos:152", "erdos:26", "erdos:741", "erdos:846" ], "targets": [], "verified": [], "first": "2026-02-14", "last": "2026-04-16", "statement_count": 9, "target_count": 0, "verified_count": 0, "line": "DeepMind prover agent", "lab": "Google DeepMind", "lab_source": "https://github.com/teorth/erdosproblems/wiki/AI-contributions-to-Erd%C5%91s-problems", "catch_all": false }, { "name": "GPT-5.4", "slug": "gpt-5-4", "claims": 10, "primary": 7, "outcomes": { "incorrect": 3, "partial": 5, "full": 2 }, "statements": [ "erdos:1041", "erdos:1148", "erdos:1198", "erdos:388", "erdos:488", "erdos:848", "erdos:852", "erdos:905", "erdos:931", "erdos:976" ], "targets": [], "verified": [], "first": "2026-03-15", "last": "2026-06-08", "statement_count": 10, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Claude Opus 4.7", "slug": "claude-opus-4-7", "claims": 9, "primary": 3, "outcomes": { "full": 8, "partial": 1 }, "statements": [ "erdos:1197", "erdos:263", "erdos:283", "erdos:351", "erdos:694", "erdos:696", "erdos:71", "erdos:750", "erdos:762" ], "targets": [], "verified": [ "erdos:762" ], "first": "2026-05-04", "last": "2026-06-21", "statement_count": 9, "target_count": 0, "verified_count": 1, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Gemini 3.1 Pro", "slug": "gemini-3-1-pro", "claims": 8, "primary": 5, "outcomes": { "full": 5, "partial": 2, "incorrect": 1 }, "statements": [ "erdos:1041", "erdos:1095", "erdos:1148", "erdos:115", "erdos:16", "erdos:433", "erdos:629", "erdos:848" ], "targets": [], "verified": [], "first": "2026-02-25", "last": "2026-05-29", "statement_count": 8, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Claude Opus 4.6", "slug": "claude-opus-4-6", "claims": 8, "primary": 4, "outcomes": { "full": 3, "unstated": 1, "incorrect": 2, "partial": 2 }, "statements": [ "erdos:1039", "erdos:1041", "erdos:1095", "erdos:1148", "erdos:115", "erdos:396", "erdos:848", "erdos:93" ], "targets": [], "verified": [], "first": "2026-02-17", "last": "2026-04-04", "statement_count": 8, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Gemini 3 Pro", "slug": "gemini-3-pro", "claims": 8, "primary": 5, "outcomes": { "full": 5, "incorrect": 3 }, "statements": [ "erdos:1148", "erdos:189", "erdos:281", "erdos:616", "erdos:871", "erdos:888", "erdos:93", "erdos:963" ], "targets": [], "verified": [], "first": "2025-12-17", "last": "2026-03-16", "statement_count": 8, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Gemini", "slug": "gemini", "claims": 8, "primary": 5, "outcomes": { "partial": 3, "incorrect": 2, "full": 3 }, "statements": [ "erdos:1026", "erdos:1099", "erdos:370", "erdos:388", "erdos:524", "erdos:647", "erdos:942", "erdos:964" ], "targets": [], "verified": [], "first": "2025-10-17", "last": "2026-03-15", "statement_count": 8, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "GPT-5.2", "slug": "gpt-5-2", "claims": 6, "primary": 5, "outcomes": { "partial": 4, "candidate": 1, "full": 1 }, "statements": [ "erdos:42", "erdos:460", "erdos:524", "erdos:689", "erdos:783", "erdos:848" ], "targets": [], "verified": [ "erdos:689" ], "first": "2025-10-29", "last": "2026-01-30", "statement_count": 6, "target_count": 0, "verified_count": 1, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Gemini 3 Flash", "slug": "gemini-3-flash", "claims": 6, "primary": 1, "outcomes": { "full": 6 }, "statements": [ "erdos:1090", "erdos:115", "erdos:281", "erdos:433", "erdos:898", "erdos:93" ], "targets": [], "verified": [], "first": "2026-01-19", "last": "2026-05-29", "statement_count": 6, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "AxiomProver", "slug": "axiomprover", "claims": 6, "primary": 1, "outcomes": { "full": 4, "partial": 1, "superseded": 1 }, "statements": [ "erdos:1134", "erdos:209", "erdos:328", "erdos:403", "erdos:441" ], "targets": [ "primes:bounded-gaps" ], "verified": [ "erdos:209", "erdos:328", "erdos:403" ], "first": "2026-06-19", "last": "2026-09-03", "statement_count": 5, "target_count": 1, "verified_count": 3, "line": "AxiomProver", "lab": "Axiom Math", "lab_source": "https://axiommath.ai/", "catch_all": false }, { "name": "AlphaProof", "slug": "alphaproof", "claims": 5, "primary": 4, "outcomes": { "full": 1, "partial": 4 }, "statements": [ "erdos:198", "erdos:477", "erdos:686", "erdos:835", "erdos:949" ], "targets": [], "verified": [], "first": "2025-08-09", "last": "2026-01-07", "statement_count": 5, "target_count": 0, "verified_count": 0, "line": "AlphaProof", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/", "catch_all": false }, { "name": "GPT-5.5 Thinking", "slug": "gpt-5-5-thinking", "claims": 5, "primary": 4, "outcomes": { "candidate": 2, "partial": 2, "full": 1 }, "statements": [ "erdos:1039", "erdos:1138", "erdos:288", "erdos:535", "erdos:873" ], "targets": [], "verified": [], "first": "2026-04-25", "last": "2026-05-08", "statement_count": 5, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT-6 Astra", "slug": "gpt-6-astra", "claims": 5, "primary": 4, "outcomes": { "full": 4, "record": 1 }, "statements": [ "millennium:NavierStokes", "pde:BoussinesqSmoothForcingBlowup", "pde:EulerSmoothForcingBlowup", "pde:PorousMediaSmoothForcingBlowup" ], "targets": [ "primes:bounded-gaps" ], "verified": [], "first": "2026-09-03", "last": "2026-09-09", "statement_count": 4, "target_count": 1, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Claude Opus 4.5", "slug": "claude-opus-4-5", "claims": 4, "primary": 3, "outcomes": { "full": 3, "incorrect": 1 }, "statements": [ "erdos:333", "erdos:871", "erdos:888", "erdos:93" ], "targets": [], "verified": [], "first": "2025-12-25", "last": "2026-02-17", "statement_count": 4, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Unspecified", "slug": "unspecified", "claims": 4, "primary": 2, "outcomes": { "full": 2, "candidate": 2 }, "statements": [ "erdos:1190", "erdos:202", "erdos:306", "erdos:906" ], "targets": [], "verified": [], "first": "2026-04-25", "last": "2026-06-19", "statement_count": 4, "target_count": 0, "verified_count": 0, "line": "Unspecified", "lab": null, "lab_source": null, "catch_all": true }, { "name": "Claude Code", "slug": "claude-code", "claims": 4, "primary": 2, "outcomes": { "partial": 1, "full": 3 }, "statements": [ "erdos:306", "erdos:694", "erdos:696", "erdos:750" ], "targets": [], "verified": [], "first": "2026-05-04", "last": "2026-06-17", "statement_count": 4, "target_count": 0, "verified_count": 0, "line": "Claude Code", "lab": "Anthropic", "lab_source": "https://claude.com/product/claude-code", "catch_all": false }, { "name": "Claude Opus 4.8", "slug": "claude-opus-4-8", "claims": 4, "primary": 2, "outcomes": { "full": 2, "partial": 2 }, "statements": [ "erdos:1054", "erdos:433", "erdos:434", "erdos:942" ], "targets": [], "verified": [], "first": "2026-05-29", "last": "2026-06-23", "statement_count": 4, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "GPT-5.6 Sol", "slug": "gpt-5-6-sol", "claims": 4, "primary": 4, "outcomes": { "full": 3, "matched": 1 }, "statements": [ "pde:BoussinesqSmoothForcingBlowup", "pde:EulerSmoothForcingBlowup", "pde:PorousMediaSmoothForcingBlowup" ], "targets": [ "borsuk:dimension" ], "verified": [], "first": "2026-08-12", "last": "2026-09-07", "statement_count": 3, "target_count": 1, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Aleph Prover", "slug": "aleph-prover", "claims": 3, "primary": 0, "outcomes": { "full": 3 }, "statements": [ "erdos:1067", "erdos:1071", "erdos:90" ], "targets": [], "verified": [], "first": "2026-01-28", "last": "2026-06-12", "statement_count": 3, "target_count": 0, "verified_count": 0, "line": "Aleph Prover", "lab": "Logical Intelligence", "lab_source": "https://logicalintelligence.com/aleph-prover", "catch_all": false }, { "name": "Seed Prover", "slug": "seed-prover", "claims": 3, "primary": 1, "outcomes": { "full": 3 }, "statements": [ "erdos:303", "erdos:493", "erdos:94" ], "targets": [], "verified": [ "erdos:94" ], "first": "2025-12-21", "last": "2026-01-15", "statement_count": 3, "target_count": 0, "verified_count": 1, "line": "Seed Prover", "lab": "ByteDance Seed", "lab_source": "https://github.com/ByteDance-Seed/Seed-Prover", "catch_all": false }, { "name": "Gemini Pro", "slug": "gemini-pro", "claims": 3, "primary": 2, "outcomes": { "full": 2, "partial": 1 }, "statements": [ "erdos:1132", "erdos:1153", "erdos:498" ], "targets": [], "verified": [], "first": "2026-03-24", "last": "2026-03-24", "statement_count": 3, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Claude Fable 5", "slug": "claude-fable-5", "claims": 3, "primary": 3, "outcomes": { "full": 2, "partial": 1 }, "statements": [ "erdos:1038", "erdos:619", "wikipedia:JacobianConjecture" ], "targets": [], "verified": [], "first": "2025-12-16", "last": "2026-07-19", "statement_count": 3, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Antigravity", "slug": "antigravity", "claims": 2, "primary": 0, "outcomes": { "full": 2 }, "statements": [ "erdos:16", "erdos:964" ], "targets": [], "verified": [], "first": "2026-02-14", "last": "2026-02-25", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Antigravity", "lab": "Google", "lab_source": "https://antigravity.google/", "catch_all": false }, { "name": "Claude Mythos", "slug": "claude-mythos", "claims": 2, "primary": 2, "outcomes": { "partial": 1, "full": 1 }, "statements": [ "erdos:52", "erdos:90" ], "targets": [], "verified": [], "first": "2026-05-26", "last": "2026-06-03", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "GPT Pro", "slug": "gpt-pro", "claims": 2, "primary": 0, "outcomes": { "full": 2 }, "statements": [ "erdos:105", "erdos:613" ], "targets": [], "verified": [ "erdos:105" ], "first": "2025-11-04", "last": "2025-11-17", "statement_count": 2, "target_count": 0, "verified_count": 1, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Claude Sonnet 4.6", "slug": "claude-sonnet-4-6", "claims": 2, "primary": 0, "outcomes": { "full": 2 }, "statements": [ "erdos:115", "erdos:433" ], "targets": [], "verified": [], "first": "2026-03-03", "last": "2026-05-29", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Trellis", "slug": "trellis", "claims": 2, "primary": 0, "outcomes": { "partial": 2 }, "statements": [ "erdos:165", "erdos:986" ], "targets": [], "verified": [], "first": "2026-06-10", "last": "2026-06-10", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Trellis", "lab": "Wes Pegden, Carnegie Mellon University", "lab_source": "https://www.math.cmu.edu/~wes/trellis.php", "catch_all": false }, { "name": "Rethlas", "slug": "rethlas", "claims": 2, "primary": 2, "outcomes": { "candidate": 2 }, "statements": [ "erdos:327", "erdos:819" ], "targets": [], "verified": [], "first": "2026-05-13", "last": "2026-05-15", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Rethlas", "lab": "FrenzyMath", "lab_source": "https://arxiv.org/abs/2604.03789", "catch_all": false }, { "name": "Claude Opus", "slug": "claude-opus", "claims": 2, "primary": 1, "outcomes": { "full": 2 }, "statements": [ "erdos:347", "erdos:498" ], "targets": [], "verified": [], "first": "2025-10-25", "last": "2025-10-25", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "Gemini 3", "slug": "gemini-3", "claims": 2, "primary": 1, "outcomes": { "full": 2 }, "statements": [ "erdos:355", "erdos:659" ], "targets": [], "verified": [], "first": "2026-01-13", "last": "2026-03-13", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Gemini Deep Think", "slug": "gemini-deep-think", "claims": 2, "primary": 2, "outcomes": { "partial": 2 }, "statements": [ "erdos:367", "erdos:686" ], "targets": [], "verified": [], "first": "2025-08-09", "last": "2025-11-22", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Seed Prover 1.5", "slug": "seed-prover-1-5", "claims": 2, "primary": 1, "outcomes": { "full": 2 }, "statements": [ "erdos:379", "erdos:958" ], "targets": [], "verified": [], "first": "2025-12-19", "last": "2025-12-21", "statement_count": 2, "target_count": 0, "verified_count": 0, "line": "Seed Prover", "lab": "ByteDance Seed", "lab_source": "https://github.com/ByteDance-Seed/Seed-Prover", "catch_all": false }, { "name": "Various", "slug": "various", "claims": 2, "primary": 1, "outcomes": { "full": 1, "record": 1 }, "statements": [ "erdos:392" ], "targets": [ "kissing:dimension-11" ], "verified": [], "first": "2026-02-23", "last": "2026-06-09", "statement_count": 1, "target_count": 1, "verified_count": 0, "line": "Various", "lab": null, "lab_source": null, "catch_all": true }, { "name": "AlphaTensor", "slug": "alphatensor", "claims": 2, "primary": 2, "outcomes": { "matched": 1, "record": 1 }, "statements": [], "targets": [ "matmul:2x2-strassen", "matmul:4x4-mod2" ], "verified": [ "matmul:2x2-strassen", "matmul:4x4-mod2" ], "first": "2022-10-05", "last": "2022-10-05", "statement_count": 0, "target_count": 2, "verified_count": 2, "line": "AlphaTensor", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/blog/discovering-novel-algorithms-with-alphatensor/", "catch_all": false }, { "name": "ChatGPT free version", "slug": "chatgpt-free-version", "claims": 1, "primary": 1, "outcomes": { "incorrect": 1 }, "statements": [ "erdos:51" ], "targets": [], "verified": [], "first": "2026-01-11", "last": "2026-01-11", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "ChatGPT", "lab": "OpenAI", "lab_source": "https://openai.com/chatgpt/", "catch_all": false }, { "name": "Numina Lean Agent", "slug": "numina-lean-agent", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:93" ], "targets": [], "verified": [], "first": "2026-02-17", "last": "2026-02-17", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Numina", "lab": "Project Numina", "lab_source": "https://projectnumina.ai/", "catch_all": false }, { "name": "ulam.ai scaffold with Gemini 3 Flash and Gemini 3.1 Pro", "slug": "ulam-ai-scaffold-with-gemini-3-flash-and-gemini-3-1-pro", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:115" ], "targets": [], "verified": [], "first": "2026-03-03", "last": "2026-03-03", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "UlamAI", "lab": "UlamAI", "lab_source": "https://www.ulam.ai/", "catch_all": false }, { "name": "Automated research pipeline", "slug": "automated-research-pipeline", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:366" ], "targets": [], "verified": [], "first": "2026-04-14", "last": "2026-04-14", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Automated research pipeline", "lab": null, "lab_source": null, "catch_all": false }, { "name": "Gemini 3.1 Deep Think", "slug": "gemini-3-1-deep-think", "claims": 1, "primary": 0, "outcomes": { "unstated": 1 }, "statements": [ "erdos:396" ], "targets": [], "verified": [], "first": "2026-04-04", "last": "2026-04-04", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Project Numina", "slug": "project-numina", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:433" ], "targets": [], "verified": [], "first": "2026-05-29", "last": "2026-05-29", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Numina", "lab": "Project Numina", "lab_source": "https://projectnumina.ai/", "catch_all": false }, { "name": "Gemini Flash", "slug": "gemini-flash", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:498" ], "targets": [], "verified": [], "first": null, "last": null, "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "Grok", "slug": "grok", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:524" ], "targets": [], "verified": [], "first": "2026-01-30", "last": "2026-01-30", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Grok", "lab": "xAI", "lab_source": "https://x.ai/grok", "catch_all": false }, { "name": "ProofCouncil", "slug": "proofcouncil", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:539" ], "targets": [], "verified": [], "first": "2026-06-10", "last": "2026-06-10", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "ProofCouncil", "lab": "ETH Zürich SRI Lab", "lab_source": "https://github.com/eth-sri/proof-council", "catch_all": false }, { "name": "Claude Sonnet 4.5", "slug": "claude-sonnet-4-5", "claims": 1, "primary": 1, "outcomes": { "incorrect": 1 }, "statements": [ "erdos:616" ], "targets": [], "verified": [], "first": "2026-01-18", "last": "2026-01-18", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Claude", "lab": "Anthropic", "lab_source": "https://claude.com/product/overview", "catch_all": false }, { "name": "DeepSeek DeepThink", "slug": "deepseek-deepthink", "claims": 1, "primary": 1, "outcomes": { "incorrect": 1 }, "statements": [ "erdos:647" ], "targets": [], "verified": [], "first": "2026-01-28", "last": "2026-01-28", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "DeepSeek", "lab": "DeepSeek", "lab_source": "https://www.deepseek.com/", "catch_all": false }, { "name": "Seed 2.0 Pro", "slug": "seed-2-0-pro", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:686" ], "targets": [], "verified": [], "first": "2025-08-09", "last": "2025-08-09", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Seed", "lab": "ByteDance Seed", "lab_source": "https://seed.bytedance.com/en/", "catch_all": false }, { "name": "Multiscalar Fields System", "slug": "multiscalar-fields-system", "claims": 1, "primary": 1, "outcomes": { "full": 1 }, "statements": [ "erdos:690" ], "targets": [], "verified": [], "first": "2026-05-08", "last": "2026-05-08", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Multiscalar Fields System", "lab": "Shouqiao Wang and Davide Crapis", "lab_source": "https://arxiv.org/abs/2605.08542", "catch_all": false }, { "name": "GPT-5.2-Codex", "slug": "gpt-5-2-codex", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:751" ], "targets": [], "verified": [], "first": "2026-01-27", "last": "2026-01-27", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Codex", "lab": "OpenAI", "lab_source": "https://openai.com/codex/", "catch_all": false }, { "name": "GPT-5.3 Instant", "slug": "gpt-5-3-instant", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:866" ], "targets": [], "verified": [], "first": "2026-05-04", "last": "2026-05-04", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "GPT-5.2 multi-agent system", "slug": "gpt-5-2-multi-agent-system", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:868" ], "targets": [], "verified": [], "first": "2026-01-13", "last": "2026-01-13", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "GPT", "lab": "OpenAI", "lab_source": "https://openai.com/index/introducing-gpt-5/", "catch_all": false }, { "name": "Archivara", "slug": "archivara", "claims": 1, "primary": 1, "outcomes": { "full": 1 }, "statements": [ "erdos:897" ], "targets": [], "verified": [], "first": "2025-12-26", "last": "2025-12-26", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Archivara", "lab": "Archivara", "lab_source": "https://x.com/spicey_lemonade/status/2004558572496035892", "catch_all": false }, { "name": "Principia Math", "slug": "principia-math", "claims": 1, "primary": 1, "outcomes": { "partial": 1 }, "statements": [ "erdos:1054" ], "targets": [], "verified": [], "first": "2026-06-23", "last": "2026-06-23", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Principia Math", "lab": "Principia Math", "lab_source": "https://www.linkedin.com/company/principia-math", "catch_all": false }, { "name": "Gemini 3.1", "slug": "gemini-3-1", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:1148" ], "targets": [], "verified": [], "first": "2026-03-17", "last": "2026-03-17", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Gemini", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/models/gemini/", "catch_all": false }, { "name": "UlamAI Prover", "slug": "ulamai-prover", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:1148" ], "targets": [], "verified": [], "first": "2026-03-17", "last": "2026-03-17", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "UlamAI", "lab": "UlamAI", "lab_source": "https://www.ulam.ai/", "catch_all": false }, { "name": "Gauss", "slug": "gauss", "claims": 1, "primary": 0, "outcomes": { "full": 1 }, "statements": [ "erdos:1196" ], "targets": [], "verified": [], "first": "2026-04-16", "last": "2026-04-16", "statement_count": 1, "target_count": 0, "verified_count": 0, "line": "Gauss", "lab": "Math Inc", "lab_source": "https://www.math.inc/gauss", "catch_all": false }, { "name": "ChatGPT", "slug": "chatgpt", "claims": 1, "primary": 1, "outcomes": { "superseded": 1 }, "statements": [], "targets": [ "primes:bounded-gaps" ], "verified": [], "first": "2026-09-01", "last": "2026-09-01", "statement_count": 0, "target_count": 1, "verified_count": 0, "line": "ChatGPT", "lab": "OpenAI", "lab_source": "https://openai.com/chatgpt/", "catch_all": false }, { "name": "FunSearch", "slug": "funsearch", "claims": 1, "primary": 1, "outcomes": { "record": 1 }, "statements": [], "targets": [ "capset:dimension-8" ], "verified": [ "capset:dimension-8" ], "first": "2023-12-14", "last": "2023-12-14", "statement_count": 0, "target_count": 1, "verified_count": 1, "line": "FunSearch", "lab": "Google DeepMind", "lab_source": "https://deepmind.google/blog/funsearch-making-new-discoveries-in-mathematical-sciences-using-large-language-models/", "catch_all": false } ]