Spaces:
Running
Running
| [ | |
| { | |
| "id": "dpid-269-sonnet", | |
| "title": "Skill, Sonnet 5.5", | |
| "model": "claude-sonnet-5-5", | |
| "effort": null, | |
| "seconds": 194, | |
| "score": { | |
| "symbols": { | |
| "pred": 189, | |
| "gt": 190, | |
| "matched": 188, | |
| "precision": 0.9947089947089947, | |
| "recall": 0.9894736842105263, | |
| "f1": 0.992084432717678, | |
| "class_accuracy": 0.8882978723404256 | |
| }, | |
| "connections": { | |
| "pred": 703, | |
| "gt": 732, | |
| "correct": 692, | |
| "precision": 0.984352773826458, | |
| "recall": 0.9453551912568307, | |
| "f1": 0.9644599303135888, | |
| "symbol_f1": 0.9554977742732979 | |
| } | |
| } | |
| }, | |
| { | |
| "id": "dpid-269-luna", | |
| "title": "Deep Agents, gpt-6-luna", | |
| "model": "gpt-6-luna", | |
| "effort": "low", | |
| "seconds": 34, | |
| "score": { | |
| "symbols": { | |
| "pred": 190, | |
| "gt": 190, | |
| "matched": 169, | |
| "precision": 0.8894736842105263, | |
| "recall": 0.8894736842105263, | |
| "f1": 0.8894736842105263, | |
| "class_accuracy": 0.7810650887573964 | |
| }, | |
| "connections": { | |
| "pred": 635, | |
| "gt": 732, | |
| "correct": 525, | |
| "precision": 0.8267716535433071, | |
| "recall": 0.7172131147540983, | |
| "f1": 0.7681053401609363, | |
| "symbol_f1": 0.7539718330958666 | |
| } | |
| } | |
| } | |
| ] |