Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial Information on Spatial and Temporal Simulation Tasks Step-level
Loading...
3.8
Subtask Accuracy
Cortex (full harness)
2.09648
2.53874
2.981
3.42326
Jul 6, 2026
Subtask Accuracy
Memory Accuracy
Total Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Subtask Accuracy
Memory Accuracy
Total Score
Cortex (full harness)
Level=Step-level
2026.07
3.8
4.254
8.053
Cortex (w/o harness)
Level=Step-level
2026.07
2.994
3.933
6.927
Cortex (harness on skills)
Level=Step-level
2026.07
2.885
4.15
7.035
Cortex (baseline)
Level=Step-level
2026.07
2.761
3.744
6.505
GPT-5
Level=Step-level
2026.07
2.755
3.668
6.422
Gemini
Level=Step-level
2026.07
2.521
4.176
6.697
Qwen3-VL-8B-Instruct
Level=Step-level
2026.07
2.162
4.263
6.424
Feedback
Search any
task
Search any
task