Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon Task on Spatial and Temporal Simulation Tasks Episode-level
Loading...
3.576
Subtask Accuracy
Cortex (full harness)
2.18448
2.54574
2.907
3.26826
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=Episode-level
2026.07
3.576
3.804
7.38
Cortex (w/o harness)
Level=Episode-level
2026.07
3.004
3.922
6.925
Gemini
Level=Episode-level
2026.07
2.774
3.87
6.644
Cortex (harness on skills)
Level=Episode-level
2026.07
2.743
4.123
6.866
GPT-5
Level=Episode-level
2026.07
2.711
4.285
6.996
Qwen3-VL-8B-Instruct
Level=Episode-level
2026.07
2.274
3.746
6.021
Cortex (baseline)
Level=Episode-level
2026.07
2.238
4.362
6.6
Feedback
Search any
task
Search any
task