Upload eval/swe_bench_results.json with huggingface_hub
Browse files- eval/swe_bench_results.json +27 -0
eval/swe_bench_results.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"always_frontier": {
|
| 3 |
+
"success": 0.782,
|
| 4 |
+
"avg_cost": 0.3166872804999999,
|
| 5 |
+
"n": 500
|
| 6 |
+
},
|
| 7 |
+
"always_cheap": {
|
| 8 |
+
"success": 0.632,
|
| 9 |
+
"avg_cost": 0.014239461958399993,
|
| 10 |
+
"n": 500
|
| 11 |
+
},
|
| 12 |
+
"aco_v8": {
|
| 13 |
+
"success": 0.756,
|
| 14 |
+
"avg_cost": 0.29145885426799994,
|
| 15 |
+
"n": 500
|
| 16 |
+
},
|
| 17 |
+
"oracle": {
|
| 18 |
+
"success": 0.87,
|
| 19 |
+
"avg_cost": 0.05456037742200003,
|
| 20 |
+
"n": 500
|
| 21 |
+
},
|
| 22 |
+
"aco_v9_feedback": {
|
| 23 |
+
"success": 0.826,
|
| 24 |
+
"avg_cost": 0.4847524783679998,
|
| 25 |
+
"n": 500
|
| 26 |
+
}
|
| 27 |
+
}
|