qedbot

Systems

Track records

73 systems across 613 claims, computed from the claims rather than authored. Not a benchmark: which problems attract attention has little to do with how hard they are.

Every system

Aristotle

198 claims·188 statements·2025-10-25 to 2026-06-23

169 full24 partial3 incorrect9 checked
AlphaEvolve

77 claims·9 statements·68 records·2025-11-03 to 2026-03-24

2 full19 records6 partial12 matched
GPT-5.5 Pro

72 claims·64 statements·2025-10-29 to 2026-06-29

25 full21 partial3 checked
GPT-5.4 Pro

45 claims·44 statements·2026-03-07 to 2026-06-21

20 full20 partial1 incorrect
GPT

43 claims·43 statements·2025-10-25 to 2026-06-27

29 full6 partial1 incorrect3 checked
GPT-5.2 Pro

30 claims·28 statements·2025-12-25 to 2026-06-19

15 full8 partial5 incorrect
Codex

29 claims·26 statements·2025-10-25 to 2026-06-29

13 full13 partial3 checked
GPT-5.2 Thinking

28 claims·27 statements·2025-08-09 to 2026-03-24

13 full13 partial2 incorrect
GPT-5

24 claims·24 statements·2025-09-29 to 2025-11-20

14 full10 partial1 checked
GPT-5.4 Thinking

19 claims·17 statements·2025-08-09 to 2026-04-29

4 full13 partial1 incorrect
Claude

18 claims·17 statements·1 records·2025-08-09 to 2026-09-04

6 full1 records8 partial3 incorrect1 checked
GPT-5.5

14 claims·13 statements·2025-12-16 to 2026-06-29

5 full6 partial
Aletheia

14 claims·14 statements·2026-01-29 to 2026-02-02

10 full4 partial
Gemini Deep Research

14 claims·14 statements·2025-10-17 to 2026-02-20

3 full10 partial1 incorrect
GPT-5.4

10 claims·10 statements·2026-03-15 to 2026-06-08

2 full5 partial3 incorrect
Claude Opus 4.7

9 claims·9 statements·2026-05-04 to 2026-06-21

8 full1 partial1 checked
Gemini 3.1 Pro

8 claims·8 statements·2026-02-25 to 2026-05-29

5 full2 partial1 incorrect
Claude Opus 4.6

8 claims·8 statements·2026-02-17 to 2026-04-04

3 full2 partial2 incorrect
Gemini 3 Pro

8 claims·8 statements·2025-12-17 to 2026-03-16

5 full3 incorrect
Gemini

8 claims·8 statements·2025-10-17 to 2026-03-15

3 full3 partial2 incorrect
GPT-5.2

6 claims·6 statements·2025-10-29 to 2026-01-30

1 full4 partial1 checked
Gemini 3 Flash

6 claims·6 statements·2026-01-19 to 2026-05-29

6 full
AlphaProof

5 claims·5 statements·2025-08-09 to 2026-01-07

1 full4 partial
AxiomProver

5 claims·5 statements·2026-06-19 to 2026-06-19

4 full1 partial3 checked
GPT-5.5 Thinking

5 claims·5 statements·2026-04-25 to 2026-05-08

1 full2 partial
Claude Opus 4.5

4 claims·4 statements·2025-12-25 to 2026-02-17

3 full1 incorrect
Unspecified

4 claims·4 statements·2026-04-25 to 2026-06-19

2 full
Claude Code

4 claims·4 statements·2026-05-04 to 2026-06-17

3 full1 partial
Claude Opus 4.8

4 claims·4 statements·2026-05-29 to 2026-06-23

2 full2 partial
Aleph Prover

3 claims·3 statements·2026-01-28 to 2026-06-12

3 full
Gemini Pro

3 claims·3 statements·2026-03-24 to 2026-03-24

2 full1 partial
Antigravity

2 claims·2 statements·2026-02-14 to 2026-02-25

2 full
Claude Mythos

2 claims·2 statements·2026-05-26 to 2026-06-03

1 full1 partial
GPT Pro

2 claims·2 statements·2025-11-04 to 2025-11-17

2 full1 checked
Trellis

2 claims·2 statements·2026-06-10 to 2026-06-10

2 partial
Seed Prover

2 claims·2 statements·2025-12-21 to 2025-12-21

2 full
Rethlas

2 claims·2 statements·2026-05-13 to 2026-05-15

Claude Opus

2 claims·2 statements·2025-10-25 to 2025-10-25

2 full
Gemini 3

2 claims·2 statements·2026-01-13 to 2026-03-13

2 full
Claude Fable 5

2 claims·2 statements·2025-12-16 to 2026-06-09

1 full1 partial
AlphaTensor

2 claims·2 records·2022-10-05 to 2022-10-05

1 records1 matched2 checked
Various

1 claim·1 statements·2026-02-23 to 2026-02-23

1 full
Project Numina

1 claim·1 statements·2026-05-29 to 2026-05-29

1 full
Grok

1 claim·1 statements·2026-01-30 to 2026-01-30

1 partial
ProofCouncil

1 claim·1 statements·2026-06-10 to 2026-06-10

1 partial
Seed 2.0 Pro

1 claim·1 statements·2025-08-09 to 2025-08-09

1 partial
GPT-5.2-Codex

1 claim·1 statements·2026-01-27 to 2026-01-27

1 full
GPT-5.3 Instant

1 claim·1 statements·2026-05-04 to 2026-05-04

1 partial
Archivara

1 claim·1 statements·2025-12-26 to 2025-12-26

1 full
Principia Math

1 claim·1 statements·2026-06-23 to 2026-06-23

1 partial
Gemini 3.1

1 claim·1 statements·2026-03-17 to 2026-03-17

1 full
UlamAI Prover

1 claim·1 statements·2026-03-17 to 2026-03-17

1 full
Gauss

1 claim·1 statements·2026-04-16 to 2026-04-16

1 full
GPT-6 Astra

1 claim·1 statements·2026-09-09 to 2026-09-09

1 full
FunSearch

1 claim·1 records·2023-12-14 to 2023-12-14

1 records1 checked