Skip to content
Merged
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
56 changes: 28 additions & 28 deletions src/data/flip_labels/flip_labels_r2-reasonometry.json
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
},
{
"global index": "ArcMMLU_16",
"flip": 1
"flip": 0
},
{
"global index": "ArcMMLU_182",
Expand All @@ -33,7 +33,7 @@
},
{
"global index": "ArcMMLU_349",
"flip": 1
"flip": 0
},
{
"global index": "ArcMMLU_378",
Expand All @@ -45,19 +45,19 @@
},
{
"global index": "ArcMMLU_496",
"flip": 1
"flip": 0
},
{
"global index": "ArcMMLU_631",
"flip": 1
"flip": 0
},
{
"global index": "ArcMMLU_646",
"flip": 0
},
{
"global index": "ArcMMLU_659",
"flip": 1
"flip": 0
},
{
"global index": "ArcMMLU_676",
Expand Down Expand Up @@ -157,23 +157,23 @@
},
{
"global index": "Ethics_deontology_0",
"flip": 1
"flip": 0
},
{
"global index": "Ethics_deontology_2",
"flip": 0
},
{
"global index": "Ethics_deontology_31",
"flip": 1
"flip": 0
},
{
"global index": "Ethics_deontology_32",
"flip": 1
"flip": 0
},
{
"global index": "Ethics_deontology_56",
"flip": 1
"flip": 0
},
{
"global index": "Ethics_justice_1",
Expand Down Expand Up @@ -413,7 +413,7 @@
},
{
"global index": "MMLUPro_biology_3225",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_business_226",
Expand Down Expand Up @@ -621,11 +621,11 @@
},
{
"global index": "MMLUPro_engineering_10701",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_engineering_10823",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_engineering_10864",
Expand Down Expand Up @@ -809,7 +809,7 @@
},
{
"global index": "MMLUPro_philosophy_9510",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_philosophy_9536",
Expand All @@ -825,7 +825,7 @@
},
{
"global index": "MMLUPro_philosophy_9943",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_physics_7773",
Expand Down Expand Up @@ -885,23 +885,23 @@
},
{
"global index": "MMLU_formal_logic_16",
"flip": 1
"flip": 0
},
{
"global index": "MMLU_formal_logic_32",
"flip": 1
"flip": 0
},
{
"global index": "MMLU_formal_logic_63",
"flip": 0
},
{
"global index": "MMLU_formal_logic_7",
"flip": 1
"flip": 0
},
{
"global index": "MMLU_formal_logic_70",
"flip": 1
"flip": 0
},
{
"global index": "MMLU_formal_logic_85",
Expand Down Expand Up @@ -965,15 +965,15 @@
},
{
"global index": "MedMCQA_1054",
"flip": 1
"flip": 0
},
{
"global index": "MedMCQA_1298",
"flip": 1
"flip": 0
},
{
"global index": "MedMCQA_1309",
"flip": 1
"flip": 0
},
{
"global index": "MedMCQA_1362",
Expand All @@ -989,7 +989,7 @@
},
{
"global index": "MedMCQA_2323",
"flip": 1
"flip": 0
},
{
"global index": "MedMCQA_2366",
Expand All @@ -1009,15 +1009,15 @@
},
{
"global index": "MedMCQA_643",
"flip": 1
"flip": 0
},
{
"global index": "MedMCQA_853",
"flip": 0
},
{
"global index": "MusicTheoryBench_126",
"flip": 1
"flip": 0
},
{
"global index": "MusicTheoryBench_14",
Expand All @@ -1037,7 +1037,7 @@
},
{
"global index": "MusicTheoryBench_189",
"flip": 1
"flip": 0
},
{
"global index": "MusicTheoryBench_240",
Expand All @@ -1057,7 +1057,7 @@
},
{
"global index": "MusicTheoryBench_70",
"flip": 1
"flip": 0
},
{
"global index": "NarrativeQA_131",
Expand Down Expand Up @@ -1137,7 +1137,7 @@
},
{
"global index": "OpenTDB_Animals_2545",
"flip": 1
"flip": 0
},
{
"global index": "OpenTDB_Animals_262",
Expand Down Expand Up @@ -1293,7 +1293,7 @@
},
{
"global index": "PubMedQA_510",
"flip": 0
"flip": 1
},
{
"global index": "PubMedQA_520",
Expand Down
22 changes: 11 additions & 11 deletions src/data/routerMetrics/leaderboard.json
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,17 @@
"Accuracy": 79.76,
"Cost per 1k": 0.7
},
{
"Router Name": "R**2: Reasonometry Router",
"Arena Score": 76.13,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 99.76,
"Latency Score": null,
"Accuracy": 78.94,
"Cost per 1k": 0.48
},
{
"Router Name": "Divyam",
"Arena Score": 75.85,
Expand Down Expand Up @@ -54,17 +65,6 @@
"Accuracy": 78.44,
"Cost per 1k": 0.49
},
{
"Router Name": "R**2: Reasonometry Router",
"Arena Score": 75.53,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 93.57,
"Latency Score": null,
"Accuracy": 78.11,
"Cost per 1k": 0.45
},
{
"Router Name": "SapientAI Auto Router",
"Arena Score": 75.41,
Expand Down
Loading