Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spatial Information on Spatial and Temporal Simulation Tasks Step-level

3.8Subtask Accuracy

Cortex (full harness)

2.096482.538742.9813.42326Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
3.84.2548.053
2026.07
2.9943.9336.927
2026.07
2.8854.157.035
2026.07
2.7613.7446.505
2026.07
2.7553.6686.422
2026.07
2.5214.1766.697
2026.07
2.1624.2636.424