Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
agent_trajectories – Dataset by cx-cmu | AlphaNeural AI
You can deploy this model and start earning money today!
cx-cmu
/
agent_trajectories
like
0
us
Views
No views yet
Model card
Files and Versions
Community
API
Agent Trajectories Dataset — Processing & Format Documentation Overview
Benchmark Records Models Passes Avg Turns Reward Type Success Rate
tau2bench 984 5 4 32.0 binary (0/1) 39.1%
swebench 747 5 4 69.6 binary (0/1) 21.4%
terminalbench 1,429 5 4 33.4 binary (0/1) 19.2%
mathhay 1,324 5 4 3.8 binary (0/1) 46.5%
search 3,270 5 4 15.0 binary (0/1) 22.1%
mcpbench 899 5 4 26.1 continuous (0–10) 13.1%
Total8,653
Models: DeepSeek-R1, DeepSeek-V3.2… See the full description on the dataset page:
https://huggingface.co/datasets/cx-cmu/agent_trajectories
.