Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
{
"claude_code_version": "2.1.322 (Claude Code)",
"entries": {
"adv-restinstance-expectation-leak|baseline": {
"arm": "baseline",
"cost_source": "priced",
"gating": false,
"incomplete": 0,
"mean_cost_usd": 0.026965,
"mean_duration_s": 77.08,
"mean_input_tokens": 489836.8,
"mean_output_tokens": 10493.2,
"mean_turns": 26.33,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-restinstance",
"task_hash": "aecee21f71999774880b80b2509398574df8bf8917c053dcc3858b04ad0b0971",
"task_id": "adv-restinstance-expectation-leak",
"turn_limit_stops": 1,
"turns_factor": 1.5
},
"adv-restinstance-expectation-leak|treatment": {
"arm": "treatment",
"cost_source": "priced",
"gating": false,
"incomplete": 0,
"mean_cost_usd": 0.030018,
"mean_duration_s": 86.32,
"mean_input_tokens": 587180.8,
"mean_output_tokens": 8671.8,
"mean_turns": 26.0,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-restinstance",
"task_hash": "aecee21f71999774880b80b2509398574df8bf8917c053dcc3858b04ad0b0971",
"task_id": "adv-restinstance-expectation-leak",
"turn_limit_stops": 4,
"turns_factor": 1.5
}
},
"harness_version": "0.1.0",
"kind": "tier-baseline",
"schema_version": 1,
"tier": "adversarial"
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,93 @@
{
"claude_code_version": "2.1.322 (Claude Code)",
"entries": {
"narrow-requests-users-01|baseline": {
"arm": "baseline",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.009859,
"mean_duration_s": 28.32,
"mean_input_tokens": 132557.3,
"mean_output_tokens": 2866.7,
"mean_turns": 11.0,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "a649e0f83496832c1f42e1c1aee15005d24ecc595133d05d8fa28b1354754a4c",
"task_id": "narrow-requests-users-01",
"turn_limit_stops": 0,
"turns_factor": 1.5
},
"narrow-requests-users-01|treatment": {
"arm": "treatment",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.032796,
"mean_duration_s": 125.93,
"mean_input_tokens": 499791.2,
"mean_output_tokens": 13815.7,
"mean_turns": 21.67,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "a649e0f83496832c1f42e1c1aee15005d24ecc595133d05d8fa28b1354754a4c",
"task_id": "narrow-requests-users-01",
"turn_limit_stops": 1,
"turns_factor": 1.5
},
"narrow-restinstance-schema-01|baseline": {
"arm": "baseline",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.011716,
"mean_duration_s": 38.74,
"mean_input_tokens": 232008.8,
"mean_output_tokens": 3515.3,
"mean_turns": 17.0,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-restinstance",
"task_hash": "bdd4fdeaac254014d77f0d3177a71c9e57315df5bdca765c63cc512a8849df64",
"task_id": "narrow-restinstance-schema-01",
"turn_limit_stops": 0,
"turns_factor": 1.5
},
"narrow-restinstance-schema-01|treatment": {
"arm": "treatment",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.032096,
"mean_duration_s": 92.27,
"mean_input_tokens": 527758.7,
"mean_output_tokens": 9892.5,
"mean_turns": 22.83,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-restinstance",
"task_hash": "bdd4fdeaac254014d77f0d3177a71c9e57315df5bdca765c63cc512a8849df64",
"task_id": "narrow-restinstance-schema-01",
"turn_limit_stops": 3,
"turns_factor": 1.5
}
},
"harness_version": "0.1.0",
"kind": "tier-baseline",
"schema_version": 1,
"tier": "narrow"
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
{
"claude_code_version": "2.1.322 (Claude Code)",
"entries": {
"partial-requests-users-01|baseline": {
"arm": "baseline",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.010817,
"mean_duration_s": 18.67,
"mean_input_tokens": 118719.3,
"mean_output_tokens": 1887.5,
"mean_turns": 11.5,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "61a51a99892fbbe4bb9bfb7a9505341483d3ba9960c49ec1ab50a9eb39854550",
"task_id": "partial-requests-users-01",
"turn_limit_stops": 0,
"turns_factor": 1.5
},
"partial-requests-users-01|treatment": {
"arm": "treatment",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.035372,
"mean_duration_s": 107.71,
"mean_input_tokens": 560272.5,
"mean_output_tokens": 12909.3,
"mean_turns": 24.17,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "61a51a99892fbbe4bb9bfb7a9505341483d3ba9960c49ec1ab50a9eb39854550",
"task_id": "partial-requests-users-01",
"turn_limit_stops": 2,
"turns_factor": 1.5
}
},
"harness_version": "0.1.0",
"kind": "tier-baseline",
"schema_version": 1,
"tier": "partial"
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
{
"claude_code_version": "2.1.322 (Claude Code)",
"entries": {
"realistic-api-testing-01|baseline": {
"arm": "baseline",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.016401,
"mean_duration_s": 41.32,
"mean_input_tokens": 242541.3,
"mean_output_tokens": 7374.3,
"mean_turns": 16.83,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "ef138fe68471123497708f07e44d03e641d2c75374da7c04248239ed3c83e5dd",
"task_id": "realistic-api-testing-01",
"turn_limit_stops": 0,
"turns_factor": 1.5
},
"realistic-api-testing-01|treatment": {
"arm": "treatment",
"cost_source": "priced",
"gating": true,
"incomplete": 0,
"mean_cost_usd": 0.037013,
"mean_duration_s": 149.54,
"mean_input_tokens": 574239.0,
"mean_output_tokens": 16853.2,
"mean_turns": 23.5,
"model": "deepseek/deepseek-v4.1-flash",
"outcome_pass_rate": 1.0,
"pass_rate": 1.0,
"provider": "openrouter",
"runs": 6,
"skill": "rf-requests",
"task_hash": "ef138fe68471123497708f07e44d03e641d2c75374da7c04248239ed3c83e5dd",
"task_id": "realistic-api-testing-01",
"turn_limit_stops": 0,
"turns_factor": 1.5
}
},
"harness_version": "0.1.0",
"kind": "tier-baseline",
"schema_version": 1,
"tier": "realistic"
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
{
"harness_version": "0.1.0",
"kind": "trigger-baseline",
"model": "deepseek/deepseek-v4.1-flash",
"provider": "openrouter",
"schema_version": 1,
"skills": {
"rf-requests": {
"train": {
"accuracy": 0.7391,
"fn": 0,
"fp": 6,
"negative_loads": 17,
"negative_runs": 33,
"positive_loads": 36,
"positive_runs": 36,
"precision": 0.6667,
"queries": 23,
"recall": 1.0,
"tn": 5,
"tp": 12
},
"validation": {
"accuracy": 0.75,
"fn": 0,
"fp": 2,
"negative_loads": 7,
"negative_runs": 12,
"positive_loads": 11,
"positive_runs": 12,
"precision": 0.6667,
"queries": 8,
"recall": 1.0,
"tn": 2,
"tp": 4
}
},
"rf-restinstance": {
"train": {
"accuracy": 0.6957,
"fn": 0,
"fp": 7,
"negative_loads": 21,
"negative_runs": 33,
"positive_loads": 36,
"positive_runs": 36,
"precision": 0.6316,
"queries": 23,
"recall": 1.0,
"tn": 4,
"tp": 12
},
"validation": {
"accuracy": 0.625,
"fn": 0,
"fp": 3,
"negative_loads": 9,
"negative_runs": 12,
"positive_loads": 12,
"positive_runs": 12,
"precision": 0.5714,
"queries": 8,
"recall": 1.0,
"tn": 1,
"tp": 4
}
}
}
}
Loading
Loading