This has since moved
The solver later closed the last two: 672 of 672, joint first on the official leaderboard, every proof through Lean 4, Comparator and AXLE.
PutnamBench is 672 formal statements from the Putnam competition, 1962 to 2025. A Ralph loop running Codex as both worker and reviewer closed 670 of them, 99.7%, including every problem in Putnam 2025.
- 1Humanfiaour report · 99.7%670
- 2Aleph Prover (Logical Intelligence)added Jan 2026 · 99.4%668
- 3Goedel-Architectadded Jun 2026 · 88.8%597
- 4Seed-Prover 1.5 (ByteDance)added Dec 2025 · 86.5%581
- 5Hilbertadded Oct 2025 · 68.8%462
- 6AxProverBase (Axiomatic AI)added Apr 2026 · 54.3%365
The two that are not closed are not closed. They are drawn as such everywhere we show this.
Closed
670/672One loop, one model family, every proof checked by Lean.
Of the benchmark
99.7%Against 99.4% for Aleph Prover, the best on the board that day.
Still open
2Not closed, and not counted.
The loop
A Ralph loop is the plainest loop there is: give an agent the same goal again and again, with the last attempt's feedback, until the goal is met or the budget runs out. Here the goal is one PutnamBench statement in its own workspace, the feedback is Lean's, and a second Codex process judges what compiles.
Swipe the diagram sideways to see all of it →
1/0 One problem, one workspace: a Codex worker writes a Lean proof.
Where the turns go
More than 90% of problems are solved within ten turns.The turn counts are from our run logs and are not published; read them as Humanfia-reported. The solver's README gives the configuration: GPT-5.5 at xhigh reasoning, a 50-turn cap per problem in each campaign, and later campaigns that retry only what is still open. For most of the benchmark the loop is not doing anything exotic: it writes a proof, the compiler objects, it fixes it, and it is done well inside the budget.
- 110 turns over 90% of problems solved by here
- 250 turns the cap per problem, per campaign
The tail is where the argument is. For the harder problems, extra turns raise the solve rate measurably: the same worker, given more rounds against the same feedback, closes problems it did not close in ten.
The model was capable of the proof the whole time. What was missing was the arrangement that let it keep going without wandering.
That is the thesis of this site, stated as an experiment.
Checking it
The official leaderboard is maintained by the PutnamBench team. A preview set of the proof files is open for review, and the full solving pipeline is public.