Mathematical Theorem Proving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
91.2Proof-level Accuracy
23
Jun 30, 2026
100Algebra Accuracy
5
Jun 4, 2026
100Algebra Score
5
Jun 4, 2026
11.9Proof-level Accuracy
3
Jun 16, 2026
6.9Proof-level Accuracy
3
Jun 16, 2026
16.2Proof-level Accuracy
3
Jun 16, 2026
163Total Spend
3
Jun 5, 2026