| { | |
| "aco_v8": { | |
| "name": "aco_v8", | |
| "success_rate": 0.796, | |
| "avg_cost": 0.7781665000000001, | |
| "model_cost": 0.7544249999999999, | |
| "tool_cost": 0.0213615, | |
| "ver_cost": 0.0023799999999999997, | |
| "avg_context_tokens": 9352.864, | |
| "verifications": 238, | |
| "avg_tools": 2.727, | |
| "escalations": 0, | |
| "downgrades": 0 | |
| }, | |
| "frontier": { | |
| "name": "always_frontier", | |
| "success_rate": 0.91, | |
| "avg_cost": 1.0413615, | |
| "model_cost": 1.0413615, | |
| "tool_cost": 0.0, | |
| "ver_cost": 0.0, | |
| "avg_context_tokens": 8000.0, | |
| "verifications": 2000, | |
| "avg_tools": 0.0, | |
| "escalations": 0, | |
| "downgrades": 0 | |
| }, | |
| "heuristic": { | |
| "name": "heuristic", | |
| "success_rate": 0.845, | |
| "avg_cost": 0.9203665, | |
| "model_cost": 0.9203665, | |
| "tool_cost": 0.0, | |
| "ver_cost": 0.0, | |
| "avg_context_tokens": 8000.0, | |
| "verifications": 2000, | |
| "avg_tools": 0.0, | |
| "escalations": 0, | |
| "downgrades": 0 | |
| }, | |
| "cheap": { | |
| "name": "always_cheap", | |
| "success_rate": 0.2985, | |
| "avg_cost": 0.07136150000000001, | |
| "model_cost": 0.07136150000000001, | |
| "tool_cost": 0.0, | |
| "ver_cost": 0.0, | |
| "avg_context_tokens": 8000.0, | |
| "verifications": 2000, | |
| "avg_tools": 0.0, | |
| "escalations": 0, | |
| "downgrades": 0 | |
| } | |
| } |