{ "generated_at": "2026-07-05T06:50:39.328401+00:00", "matrix": [ { "model": "gpt-5-nano", "reasoning_effort": "minimal" }, { "model": "gpt-5-mini", "reasoning_effort": "minimal" }, { "model": "gpt-5", "reasoning_effort": "minimal" } ], "results": { "gpt-5-nano@minimal": { "n_docs": 10, "errors": 0, "micro_f1": 0.8963, "macro_f1": 0.8852, "doc_exact_match": 0.4, "mean_latency_ms": 5098.0, "mean_cost_usd": 0.011635, "total_cost_usd": 0.1164, "wall_time_s": 51.0 }, "gpt-5-mini@minimal": { "n_docs": 10, "errors": 0, "micro_f1": 0.8639, "macro_f1": 0.9274, "doc_exact_match": 0.4, "mean_latency_ms": 6115.0, "mean_cost_usd": 0.012694, "total_cost_usd": 0.1269, "wall_time_s": 61.16 }, "gpt-5@minimal": { "n_docs": 10, "errors": 0, "micro_f1": 0.8843, "macro_f1": 0.9393, "doc_exact_match": 0.3, "mean_latency_ms": 5377.0, "mean_cost_usd": 0.011822, "total_cost_usd": 0.1183, "wall_time_s": 53.78 } } }