LTL Instruction Following
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Success Rate (SR)
19
Feb 27, 2026
97Success Rate (SR)
18
Feb 27, 2026
914µacc
14
Feb 27, 2026
100Success Rate (SR)
12
Feb 27, 2026
7.13µAcc
10
Feb 27, 2026
24.1Accuracy (µacc)
4
Feb 27, 2026
11.67µAcc
4
Feb 27, 2026
91.9Success Rate
3
Feb 26, 2026
93.6Success Rate
3
Feb 26, 2026
74.3Success Rate
3
Feb 26, 2026
0.927SR
3
Feb 26, 2026
82.6SR
3
Feb 26, 2026
95.2Success Rate
3
Feb 26, 2026
99.3SR
3
Feb 26, 2026
0.767Success Rate
3
Feb 26, 2026
86Success Rate
3
Feb 26, 2026
95.7Success Rate
3
Feb 26, 2026
—
—Accuracy (µacc)
0
Feb 26, 2026
—
—Accuracy
0
Feb 26, 2026
—
—Success Rate
0
Feb 26, 2026
—
—Success Rate
0
Feb 26, 2026
—
—µAcc
0
Feb 26, 2026
—
—µAcc
0
Feb 26, 2026
—
—Success Rate
0
Feb 26, 2026
—
—Success Rate
0
Feb 26, 2026