[KongchangAI]
Benchmark

Formal Core Bench

A benchmark test set in the field of formal mathematics and theorem proving, used to evaluate system solve rates.

Timeline (last 90 days)

Nov 17

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.

Unverified50%

All Facts (1)

Source Articles