diff --git a/data/leaderboard.json b/data/leaderboard.json index 82e30652..8a7c4b49 100644 --- a/data/leaderboard.json +++ b/data/leaderboard.json @@ -53,6 +53,7 @@ "EvoScientist (0.1.1)", "InnoClaw", "Open Science", + "OpenEvo (v0.1.10)", "Qiushi Engine", "ResearchHarness (Claude-Opus-4.6)", "ResearchHarness (Claude-Opus-4.7)", @@ -3742,6 +3743,368 @@ "details_exported": false } }, + "OpenEvo (v0.1.10)": { + "Astronomy_000": { + "score": 40.6, + "run_id": "Astronomy_000_20260817_164021", + "duration_seconds": 258.102, + "cost_usd": 0.967882, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Astronomy_001": { + "score": 41.6, + "run_id": "Astronomy_001_20260817_164021", + "duration_seconds": 420.949, + "cost_usd": 1.578559, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Astronomy_002": { + "score": 35.0, + "run_id": "Astronomy_002_20260817_164021", + "duration_seconds": 587.18, + "cost_usd": 2.201925, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Astronomy_003": { + "score": 62.0, + "run_id": "Astronomy_003_20260817_164021", + "duration_seconds": 294.963, + "cost_usd": 1.106111, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Chemistry_000": { + "score": 29.1, + "run_id": "Chemistry_000_20260817_164021", + "duration_seconds": 1500.558, + "cost_usd": 5.627092, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Chemistry_001": { + "score": 22.75, + "run_id": "Chemistry_001_20260817_164021", + "duration_seconds": 541.387, + "cost_usd": 2.030201, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Chemistry_002": { + "score": 24.8, + "run_id": "Chemistry_002_20260817_164021", + "duration_seconds": 397.362, + "cost_usd": 1.490107, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Chemistry_003": { + "score": 33.3, + "run_id": "Chemistry_003_20260817_164021", + "duration_seconds": 1694.955, + "cost_usd": 6.356081, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Earth_000": { + "score": 25.5, + "run_id": "Earth_000_20260817_164021", + "duration_seconds": 409.626, + "cost_usd": 1.536097, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Earth_001": { + "score": 39.61, + "run_id": "Earth_001_20260817_164021", + "duration_seconds": 422.002, + "cost_usd": 1.582507, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Earth_002": { + "score": 31.1, + "run_id": "Earth_002_20260817_164021", + "duration_seconds": 973.86, + "cost_usd": 3.651975, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Earth_003": { + "score": 22.8, + "run_id": "Earth_003_20260817_164021", + "duration_seconds": 385.207, + "cost_usd": 1.444526, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Energy_000": { + "score": 19.6, + "run_id": "Energy_000_20260817_164021", + "duration_seconds": 936.944, + "cost_usd": 3.51354, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Energy_001": { + "score": 45.2, + "run_id": "Energy_001_20260817_164021", + "duration_seconds": 468.291, + "cost_usd": 1.756091, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Energy_002": { + "score": 41.3, + "run_id": "Energy_002_20260817_164021", + "duration_seconds": 900.269, + "cost_usd": 3.376009, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Energy_003": { + "score": 29.4, + "run_id": "Energy_003_20260817_164021", + "duration_seconds": 400.317, + "cost_usd": 1.501189, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Information_000": { + "score": 32.8, + "run_id": "Information_000_20260817_164021", + "duration_seconds": 968.455, + "cost_usd": 3.631706, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Information_001": { + "score": 50.8, + "run_id": "Information_001_20260817_164021", + "duration_seconds": 391.78, + "cost_usd": 1.469175, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Information_002": { + "score": 51.1, + "run_id": "Information_002_20260817_164021", + "duration_seconds": 334.695, + "cost_usd": 1.255106, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Information_003": { + "score": 18.0, + "run_id": "Information_003_20260817_164021", + "duration_seconds": 656.718, + "cost_usd": 2.462692, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Life_000": { + "score": 20.3, + "run_id": "Life_000_20260817_164021", + "duration_seconds": 319.587, + "cost_usd": 1.198451, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Life_001": { + "score": 15.4, + "run_id": "Life_001_20260817_164021", + "duration_seconds": 300.501, + "cost_usd": 1.126879, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Life_002": { + "score": 42.8, + "run_id": "Life_002_20260817_164021", + "duration_seconds": 498.708, + "cost_usd": 1.870155, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Life_003": { + "score": 36.6, + "run_id": "Life_003_20260817_164021", + "duration_seconds": 362.996, + "cost_usd": 1.361235, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Material_000": { + "score": 34.4, + "run_id": "Material_000_20260817_164021", + "duration_seconds": 821.462, + "cost_usd": 3.080482, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Material_001": { + "score": 20.8, + "run_id": "Material_001_20260817_164021", + "duration_seconds": 648.272, + "cost_usd": 2.43102, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Material_002": { + "score": 21.73, + "run_id": "Material_002_20260817_164021", + "duration_seconds": 370.911, + "cost_usd": 1.390916, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Material_003": { + "score": 22.85, + "run_id": "Material_003_20260817_164021", + "duration_seconds": 447.281, + "cost_usd": 1.677304, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Math_000": { + "score": 25.8, + "run_id": "Math_000_20260817_164021", + "duration_seconds": 458.545, + "cost_usd": 1.719544, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Math_001": { + "score": 47.6, + "run_id": "Math_001_20260817_164021", + "duration_seconds": 294.979, + "cost_usd": 1.106171, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Math_002": { + "score": 28.2, + "run_id": "Math_002_20260817_164021", + "duration_seconds": 936.189, + "cost_usd": 3.510709, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Math_003": { + "score": 8.8, + "run_id": "Math_003_20260817_164021", + "duration_seconds": 365.11, + "cost_usd": 1.369162, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Neuroscience_000": { + "score": 22.2, + "run_id": "Neuroscience_000_20260817_164021", + "duration_seconds": 1936.802, + "cost_usd": 7.263007, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Neuroscience_001": { + "score": 15.4, + "run_id": "Neuroscience_001_20260817_164021", + "duration_seconds": 493.863, + "cost_usd": 1.851986, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Neuroscience_002": { + "score": 11.15, + "run_id": "Neuroscience_002_20260817_164021", + "duration_seconds": 418.213, + "cost_usd": 1.568299, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Neuroscience_003": { + "score": 31.85, + "run_id": "Neuroscience_003_20260817_164021", + "duration_seconds": 748.139, + "cost_usd": 2.805521, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Physics_000": { + "score": 42.4, + "run_id": "Physics_000_20260817_164021", + "duration_seconds": 512.914, + "cost_usd": 1.923427, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Physics_001": { + "score": 43.4, + "run_id": "Physics_001_20260817_164021", + "duration_seconds": 1003.191, + "cost_usd": 3.761966, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Physics_002": { + "score": 53.85, + "run_id": "Physics_002_20260817_164021", + "duration_seconds": 411.83, + "cost_usd": 1.544362, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + }, + "Physics_003": { + "score": 65.6, + "run_id": "Physics_003_20260817_164021", + "duration_seconds": 482.576, + "cost_usd": 1.80966, + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "details_exported": false + } + }, "Qiushi Engine": { "Astronomy_000": { "score": 33.6, @@ -10720,26 +11083,26 @@ "Astronomy_000": 43.6, "Astronomy_001": 45.2, "Astronomy_002": 35.3, - "Astronomy_003": 53.4, - "Chemistry_000": 25.6, - "Chemistry_001": 16.4, - "Chemistry_002": 17.65, + "Astronomy_003": 62.0, + "Chemistry_000": 29.1, + "Chemistry_001": 22.75, + "Chemistry_002": 24.8, "Chemistry_003": 42.9, "Earth_000": 30.7, "Earth_001": 46.94, "Earth_002": 34.0, - "Earth_003": 10.5, + "Earth_003": 22.8, "Energy_000": 24.9, - "Energy_001": 39.4, + "Energy_001": 45.2, "Energy_002": 44.1, - "Energy_003": 28.7, + "Energy_003": 29.4, "Information_000": 49.4, - "Information_001": 21.0, - "Information_002": 49.1, + "Information_001": 50.8, + "Information_002": 51.1, "Information_003": 23.7, - "Life_000": 14.05, + "Life_000": 20.3, "Life_001": 32.15, - "Life_002": 20.7, + "Life_002": 42.8, "Life_003": 45.9, "Material_000": 34.5, "Material_001": 37.0, @@ -10747,15 +11110,15 @@ "Material_003": 56.85, "Math_000": 47.95, "Math_001": 49.6, - "Math_002": 20.7, + "Math_002": 28.2, "Math_003": 29.6, - "Neuroscience_000": 14.2, + "Neuroscience_000": 22.2, "Neuroscience_001": 22.25, "Neuroscience_002": 12.7, "Neuroscience_003": 39.2, - "Physics_000": 38.6, + "Physics_000": 42.4, "Physics_001": 49.0, - "Physics_002": 47.4, - "Physics_003": 60.5 + "Physics_002": 53.85, + "Physics_003": 65.6 } } \ No newline at end of file diff --git a/data/leaderboard_only_runs.json b/data/leaderboard_only_runs.json index 5fd4ac14..c1ef3700 100644 --- a/data/leaderboard_only_runs.json +++ b/data/leaderboard_only_runs.json @@ -2014,6 +2014,526 @@ "total_score": 47.8, "details_exported": false }, + { + "run_id": "Astronomy_000_20260817_164021", + "task_id": "Astronomy_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 258.102, + "cost_usd": 0.967882, + "total_score": 40.6, + "details_exported": false + }, + { + "run_id": "Astronomy_001_20260817_164021", + "task_id": "Astronomy_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 420.949, + "cost_usd": 1.578559, + "total_score": 41.6, + "details_exported": false + }, + { + "run_id": "Astronomy_002_20260817_164021", + "task_id": "Astronomy_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 587.18, + "cost_usd": 2.201925, + "total_score": 35.0, + "details_exported": false + }, + { + "run_id": "Astronomy_003_20260817_164021", + "task_id": "Astronomy_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 294.963, + "cost_usd": 1.106111, + "total_score": 62.0, + "details_exported": false + }, + { + "run_id": "Chemistry_000_20260817_164021", + "task_id": "Chemistry_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1500.558, + "cost_usd": 5.627092, + "total_score": 29.1, + "details_exported": false + }, + { + "run_id": "Chemistry_001_20260817_164021", + "task_id": "Chemistry_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 541.387, + "cost_usd": 2.030201, + "total_score": 22.75, + "details_exported": false + }, + { + "run_id": "Chemistry_002_20260817_164021", + "task_id": "Chemistry_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 397.362, + "cost_usd": 1.490107, + "total_score": 24.8, + "details_exported": false + }, + { + "run_id": "Chemistry_003_20260817_164021", + "task_id": "Chemistry_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1694.955, + "cost_usd": 6.356081, + "total_score": 33.3, + "details_exported": false + }, + { + "run_id": "Earth_000_20260817_164021", + "task_id": "Earth_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 409.626, + "cost_usd": 1.536097, + "total_score": 25.5, + "details_exported": false + }, + { + "run_id": "Earth_001_20260817_164021", + "task_id": "Earth_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 422.002, + "cost_usd": 1.582507, + "total_score": 39.61, + "details_exported": false + }, + { + "run_id": "Earth_002_20260817_164021", + "task_id": "Earth_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 973.86, + "cost_usd": 3.651975, + "total_score": 31.1, + "details_exported": false + }, + { + "run_id": "Earth_003_20260817_164021", + "task_id": "Earth_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 385.207, + "cost_usd": 1.444526, + "total_score": 22.8, + "details_exported": false + }, + { + "run_id": "Energy_000_20260817_164021", + "task_id": "Energy_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 936.944, + "cost_usd": 3.51354, + "total_score": 19.6, + "details_exported": false + }, + { + "run_id": "Energy_001_20260817_164021", + "task_id": "Energy_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 468.291, + "cost_usd": 1.756091, + "total_score": 45.2, + "details_exported": false + }, + { + "run_id": "Energy_002_20260817_164021", + "task_id": "Energy_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 900.269, + "cost_usd": 3.376009, + "total_score": 41.3, + "details_exported": false + }, + { + "run_id": "Energy_003_20260817_164021", + "task_id": "Energy_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 400.317, + "cost_usd": 1.501189, + "total_score": 29.4, + "details_exported": false + }, + { + "run_id": "Information_000_20260817_164021", + "task_id": "Information_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 968.455, + "cost_usd": 3.631706, + "total_score": 32.8, + "details_exported": false + }, + { + "run_id": "Information_001_20260817_164021", + "task_id": "Information_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 391.78, + "cost_usd": 1.469175, + "total_score": 50.8, + "details_exported": false + }, + { + "run_id": "Information_002_20260817_164021", + "task_id": "Information_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 334.695, + "cost_usd": 1.255106, + "total_score": 51.1, + "details_exported": false + }, + { + "run_id": "Information_003_20260817_164021", + "task_id": "Information_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 656.718, + "cost_usd": 2.462692, + "total_score": 18.0, + "details_exported": false + }, + { + "run_id": "Life_000_20260817_164021", + "task_id": "Life_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 319.587, + "cost_usd": 1.198451, + "total_score": 20.3, + "details_exported": false + }, + { + "run_id": "Life_001_20260817_164021", + "task_id": "Life_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 300.501, + "cost_usd": 1.126879, + "total_score": 15.4, + "details_exported": false + }, + { + "run_id": "Life_002_20260817_164021", + "task_id": "Life_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 498.708, + "cost_usd": 1.870155, + "total_score": 42.8, + "details_exported": false + }, + { + "run_id": "Life_003_20260817_164021", + "task_id": "Life_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 362.996, + "cost_usd": 1.361235, + "total_score": 36.6, + "details_exported": false + }, + { + "run_id": "Material_000_20260817_164021", + "task_id": "Material_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 821.462, + "cost_usd": 3.080482, + "total_score": 34.4, + "details_exported": false + }, + { + "run_id": "Material_001_20260817_164021", + "task_id": "Material_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 648.272, + "cost_usd": 2.43102, + "total_score": 20.8, + "details_exported": false + }, + { + "run_id": "Material_002_20260817_164021", + "task_id": "Material_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 370.911, + "cost_usd": 1.390916, + "total_score": 21.73, + "details_exported": false + }, + { + "run_id": "Material_003_20260817_164021", + "task_id": "Material_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 447.281, + "cost_usd": 1.677304, + "total_score": 22.85, + "details_exported": false + }, + { + "run_id": "Math_000_20260817_164021", + "task_id": "Math_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 458.545, + "cost_usd": 1.719544, + "total_score": 25.8, + "details_exported": false + }, + { + "run_id": "Math_001_20260817_164021", + "task_id": "Math_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 294.979, + "cost_usd": 1.106171, + "total_score": 47.6, + "details_exported": false + }, + { + "run_id": "Math_002_20260817_164021", + "task_id": "Math_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 936.189, + "cost_usd": 3.510709, + "total_score": 28.2, + "details_exported": false + }, + { + "run_id": "Math_003_20260817_164021", + "task_id": "Math_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 365.11, + "cost_usd": 1.369162, + "total_score": 8.8, + "details_exported": false + }, + { + "run_id": "Neuroscience_000_20260817_164021", + "task_id": "Neuroscience_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1936.802, + "cost_usd": 7.263007, + "total_score": 22.2, + "details_exported": false + }, + { + "run_id": "Neuroscience_001_20260817_164021", + "task_id": "Neuroscience_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 493.863, + "cost_usd": 1.851986, + "total_score": 15.4, + "details_exported": false + }, + { + "run_id": "Neuroscience_002_20260817_164021", + "task_id": "Neuroscience_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 418.213, + "cost_usd": 1.568299, + "total_score": 11.15, + "details_exported": false + }, + { + "run_id": "Neuroscience_003_20260817_164021", + "task_id": "Neuroscience_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 748.139, + "cost_usd": 2.805521, + "total_score": 31.85, + "details_exported": false + }, + { + "run_id": "Physics_000_20260817_164021", + "task_id": "Physics_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 512.914, + "cost_usd": 1.923427, + "total_score": 42.4, + "details_exported": false + }, + { + "run_id": "Physics_001_20260817_164021", + "task_id": "Physics_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1003.191, + "cost_usd": 3.761966, + "total_score": 43.4, + "details_exported": false + }, + { + "run_id": "Physics_002_20260817_164021", + "task_id": "Physics_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 411.83, + "cost_usd": 1.544362, + "total_score": 53.85, + "details_exported": false + }, + { + "run_id": "Physics_003_20260817_164021", + "task_id": "Physics_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 482.576, + "cost_usd": 1.80966, + "total_score": 65.6, + "details_exported": false + }, { "run_id": "Astronomy_000_20260713_195518", "task_id": "Astronomy_000", diff --git a/data/runs_index.json b/data/runs_index.json index ef21e07e..b5a93f60 100644 --- a/data/runs_index.json +++ b/data/runs_index.json @@ -15674,5 +15674,525 @@ "cost_usd": 0.2325, "total_score": 45.4, "details_exported": false + }, + { + "run_id": "Astronomy_000_20260817_164021", + "task_id": "Astronomy_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 258.102, + "cost_usd": 0.967882, + "total_score": 40.6, + "details_exported": false + }, + { + "run_id": "Astronomy_001_20260817_164021", + "task_id": "Astronomy_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 420.949, + "cost_usd": 1.578559, + "total_score": 41.6, + "details_exported": false + }, + { + "run_id": "Astronomy_002_20260817_164021", + "task_id": "Astronomy_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 587.18, + "cost_usd": 2.201925, + "total_score": 35.0, + "details_exported": false + }, + { + "run_id": "Astronomy_003_20260817_164021", + "task_id": "Astronomy_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 294.963, + "cost_usd": 1.106111, + "total_score": 62.0, + "details_exported": false + }, + { + "run_id": "Chemistry_000_20260817_164021", + "task_id": "Chemistry_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1500.558, + "cost_usd": 5.627092, + "total_score": 29.1, + "details_exported": false + }, + { + "run_id": "Chemistry_001_20260817_164021", + "task_id": "Chemistry_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 541.387, + "cost_usd": 2.030201, + "total_score": 22.75, + "details_exported": false + }, + { + "run_id": "Chemistry_002_20260817_164021", + "task_id": "Chemistry_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 397.362, + "cost_usd": 1.490107, + "total_score": 24.8, + "details_exported": false + }, + { + "run_id": "Chemistry_003_20260817_164021", + "task_id": "Chemistry_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1694.955, + "cost_usd": 6.356081, + "total_score": 33.3, + "details_exported": false + }, + { + "run_id": "Earth_000_20260817_164021", + "task_id": "Earth_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 409.626, + "cost_usd": 1.536097, + "total_score": 25.5, + "details_exported": false + }, + { + "run_id": "Earth_001_20260817_164021", + "task_id": "Earth_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 422.002, + "cost_usd": 1.582507, + "total_score": 39.61, + "details_exported": false + }, + { + "run_id": "Earth_002_20260817_164021", + "task_id": "Earth_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 973.86, + "cost_usd": 3.651975, + "total_score": 31.1, + "details_exported": false + }, + { + "run_id": "Earth_003_20260817_164021", + "task_id": "Earth_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 385.207, + "cost_usd": 1.444526, + "total_score": 22.8, + "details_exported": false + }, + { + "run_id": "Energy_000_20260817_164021", + "task_id": "Energy_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 936.944, + "cost_usd": 3.51354, + "total_score": 19.6, + "details_exported": false + }, + { + "run_id": "Energy_001_20260817_164021", + "task_id": "Energy_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 468.291, + "cost_usd": 1.756091, + "total_score": 45.2, + "details_exported": false + }, + { + "run_id": "Energy_002_20260817_164021", + "task_id": "Energy_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 900.269, + "cost_usd": 3.376009, + "total_score": 41.3, + "details_exported": false + }, + { + "run_id": "Energy_003_20260817_164021", + "task_id": "Energy_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 400.317, + "cost_usd": 1.501189, + "total_score": 29.4, + "details_exported": false + }, + { + "run_id": "Information_000_20260817_164021", + "task_id": "Information_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 968.455, + "cost_usd": 3.631706, + "total_score": 32.8, + "details_exported": false + }, + { + "run_id": "Information_001_20260817_164021", + "task_id": "Information_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 391.78, + "cost_usd": 1.469175, + "total_score": 50.8, + "details_exported": false + }, + { + "run_id": "Information_002_20260817_164021", + "task_id": "Information_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 334.695, + "cost_usd": 1.255106, + "total_score": 51.1, + "details_exported": false + }, + { + "run_id": "Information_003_20260817_164021", + "task_id": "Information_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 656.718, + "cost_usd": 2.462692, + "total_score": 18.0, + "details_exported": false + }, + { + "run_id": "Life_000_20260817_164021", + "task_id": "Life_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 319.587, + "cost_usd": 1.198451, + "total_score": 20.3, + "details_exported": false + }, + { + "run_id": "Life_001_20260817_164021", + "task_id": "Life_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 300.501, + "cost_usd": 1.126879, + "total_score": 15.4, + "details_exported": false + }, + { + "run_id": "Life_002_20260817_164021", + "task_id": "Life_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 498.708, + "cost_usd": 1.870155, + "total_score": 42.8, + "details_exported": false + }, + { + "run_id": "Life_003_20260817_164021", + "task_id": "Life_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 362.996, + "cost_usd": 1.361235, + "total_score": 36.6, + "details_exported": false + }, + { + "run_id": "Material_000_20260817_164021", + "task_id": "Material_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 821.462, + "cost_usd": 3.080482, + "total_score": 34.4, + "details_exported": false + }, + { + "run_id": "Material_001_20260817_164021", + "task_id": "Material_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 648.272, + "cost_usd": 2.43102, + "total_score": 20.8, + "details_exported": false + }, + { + "run_id": "Material_002_20260817_164021", + "task_id": "Material_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 370.911, + "cost_usd": 1.390916, + "total_score": 21.73, + "details_exported": false + }, + { + "run_id": "Material_003_20260817_164021", + "task_id": "Material_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 447.281, + "cost_usd": 1.677304, + "total_score": 22.85, + "details_exported": false + }, + { + "run_id": "Math_000_20260817_164021", + "task_id": "Math_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 458.545, + "cost_usd": 1.719544, + "total_score": 25.8, + "details_exported": false + }, + { + "run_id": "Math_001_20260817_164021", + "task_id": "Math_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 294.979, + "cost_usd": 1.106171, + "total_score": 47.6, + "details_exported": false + }, + { + "run_id": "Math_002_20260817_164021", + "task_id": "Math_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 936.189, + "cost_usd": 3.510709, + "total_score": 28.2, + "details_exported": false + }, + { + "run_id": "Math_003_20260817_164021", + "task_id": "Math_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 365.11, + "cost_usd": 1.369162, + "total_score": 8.8, + "details_exported": false + }, + { + "run_id": "Neuroscience_000_20260817_164021", + "task_id": "Neuroscience_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1936.802, + "cost_usd": 7.263007, + "total_score": 22.2, + "details_exported": false + }, + { + "run_id": "Neuroscience_001_20260817_164021", + "task_id": "Neuroscience_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 493.863, + "cost_usd": 1.851986, + "total_score": 15.4, + "details_exported": false + }, + { + "run_id": "Neuroscience_002_20260817_164021", + "task_id": "Neuroscience_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 418.213, + "cost_usd": 1.568299, + "total_score": 11.15, + "details_exported": false + }, + { + "run_id": "Neuroscience_003_20260817_164021", + "task_id": "Neuroscience_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 748.139, + "cost_usd": 2.805521, + "total_score": 31.85, + "details_exported": false + }, + { + "run_id": "Physics_000_20260817_164021", + "task_id": "Physics_000", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 512.914, + "cost_usd": 1.923427, + "total_score": 42.4, + "details_exported": false + }, + { + "run_id": "Physics_001_20260817_164021", + "task_id": "Physics_001", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 1003.191, + "cost_usd": 3.761966, + "total_score": 43.4, + "details_exported": false + }, + { + "run_id": "Physics_002_20260817_164021", + "task_id": "Physics_002", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 411.83, + "cost_usd": 1.544362, + "total_score": 53.85, + "details_exported": false + }, + { + "run_id": "Physics_003_20260817_164021", + "task_id": "Physics_003", + "timestamp": "20260817_164021", + "status": "completed", + "agent_name": "OpenEvo (v0.1.10)", + "model": "gpt-5.5", + "model_display": "GPT-5.5", + "duration_seconds": 482.576, + "cost_usd": 1.80966, + "total_score": 65.6, + "details_exported": false } -] \ No newline at end of file +]