Symbolic Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.3Solve Rate
4
Feb 26, 2026
87.7Accuracy
3
Mar 6, 2026
89.34Accuracy
3
Mar 6, 2026
9.9Pass@1
3
Mar 6, 2026
84Accuracy (BBH Symbolic Reasoning)
3
Mar 5, 2026
90.2Accuracy
3
Feb 27, 2026
98.6Accuracy
3
Feb 27, 2026
100Accuracy
3
Feb 27, 2026
63Accuracy
3
Feb 27, 2026
94.8Accuracy
3
Feb 27, 2026
95.1Solve Rate
3
Feb 26, 2026
95.1pass@1
2
Feb 26, 2026
91.4Accuracy (format-specific)
2
Feb 27, 2026
57.6Accuracy (format-specific)
2
Feb 27, 2026
41.7Baseline Accuracy
1
May 12, 2026
—
—Accuracy
0
Feb 26, 2026
—
—Accuracy
0
Feb 26, 2026
—
—Accuracy
0
Feb 26, 2026