Putnam Bench
A benchmark test set for evaluating automated theorem proving systems, containing a large number of formalized proof problems of the mathematical competition type.
Timeline (last 90 days)
Under matching the same model and comparable budgets, H1 matches or Pareto-dominates custom systems on multiple benchmarks including Putnam Bench, and has solved eight open conjecture problems.
On Putnam Bench, when using the same model as Goedel Architect, H1 is cheaper but performs better.
When using GPT 5.6 Sol, H1 achieves a 90-100 solve rate on FateX, 178% on FC100 Soft, 23-14% on Formal Core Bench, solves all 6 problems of IMO2026, and solves 670 of the 672 problems in Putnam Bench.
All Facts (3)
Under matching the same model and comparable budgets, H1 matches or Pareto-dominates custom systems on multiple benchmarks including Putnam Bench, and has solved eight open conjecture problems.
50%UnverifiedOn Putnam Bench, when using the same model as Goedel Architect, H1 is cheaper but performs better.
50%UnverifiedWhen using GPT 5.6 Sol, H1 achieves a 90-100 solve rate on FateX, 178% on FC100 Soft, 23-14% on Formal Core Bench, solves all 6 problems of IMO2026, and solves 670 of the 672 problems in Putnam Bench.
50%