Skip to content

Sync leaderboard data from RouterArena #48

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yl231 merged 1 commit into from
Jun 20, 2026
Merged

Sync leaderboard data from RouterArena #48

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
62 changes: 31 additions & 31 deletions src/data/flip_labels/flip_labels_vllm-sr.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,11 +221,11 @@
},
{
"global index": "FinQA_56",
"flip": 0
"flip": 1
},
{
"global index": "FinQA_60",
"flip": 0
"flip": 1
},
{
"global index": "GSM8K_43",
Expand Down Expand Up @@ -297,39 +297,39 @@
},
{
"global index": "GeoGraphyData_100k_42",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_105",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_114",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_118",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_131",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_136",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_181",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_237",
"flip": 0
},
{
"global index": "LiveCodeBench_271",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_350",
Expand All @@ -345,7 +345,7 @@
},
{
"global index": "LiveCodeBench_43",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_431",
Expand All @@ -357,23 +357,23 @@
},
{
"global index": "LiveCodeBench_476",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_485",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_49",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_491",
"flip": 0
"flip": 1
},
{
"global index": "LiveCodeBench_499",
"flip": 0
"flip": 1
},
{
"global index": "MATH_108",
Expand Down Expand Up @@ -437,7 +437,7 @@
},
{
"global index": "MMLUPro_business_507",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_business_6",
Expand Down Expand Up @@ -645,7 +645,7 @@
},
{
"global index": "MMLUPro_health_5144",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_health_5214",
Expand Down Expand Up @@ -841,7 +841,7 @@
},
{
"global index": "MMLUPro_physics_8888",
"flip": 1
"flip": 0
},
{
"global index": "MMLUPro_physics_9017",
Expand Down Expand Up @@ -961,7 +961,7 @@
},
{
"global index": "MedMCQA_1005",
"flip": 0
"flip": 1
},
{
"global index": "MedMCQA_1054",
Expand Down Expand Up @@ -1061,7 +1061,7 @@
},
{
"global index": "NarrativeQA_131",
"flip": 1
"flip": 0
},
{
"global index": "NarrativeQA_1683",
Expand Down Expand Up @@ -1357,7 +1357,7 @@
},
{
"global index": "QANTA_Fine Arts_1212",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Fine Arts_1702",
Expand All @@ -1369,7 +1369,7 @@
},
{
"global index": "QANTA_Fine Arts_865",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Geography_1023",
Expand All @@ -1385,15 +1385,15 @@
},
{
"global index": "QANTA_History_1084",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_History_1154",
"flip": 0
},
{
"global index": "QANTA_History_433",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_History_473",
Expand Down Expand Up @@ -1421,7 +1421,7 @@
},
{
"global index": "QANTA_Literature_1727",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Literature_1843",
Expand All @@ -1433,11 +1433,11 @@
},
{
"global index": "QANTA_Literature_408",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Literature_475",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Literature_833",
Expand All @@ -1461,7 +1461,7 @@
},
{
"global index": "QANTA_Science_1473",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Science_308",
Expand All @@ -1477,11 +1477,11 @@
},
{
"global index": "QANTA_Social Science_2",
"flip": 0
"flip": 1
},
{
"global index": "QANTA_Social Science_77",
"flip": 0
"flip": 1
},
{
"global index": "SocialiQA_13810",
Expand Down
64 changes: 32 additions & 32 deletions src/data/routerMetrics/leaderboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,4 @@
[
{
"Router Name": "vllm",
"Arena Score": 75.38,
"Optimal Selection Score": 20.12,
"Optimal Cost Score": 24.52,
"Optimal Acc. Score": 89.87,
"Robustness Score": 73.1,
"Latency Score": null,
"Accuracy": 75.97,
"Cost per 1k": 0.11
},
{
"Router Name": "Sqwish Router",
"Arena Score": 75.27,
Expand All @@ -32,17 +21,6 @@
"Accuracy": 74.72,
"Cost per 1k": 0.13
},
{
"Router Name": "Nadir Router",
"Arena Score": 73.33,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 25.48,
"Latency Score": null,
"Accuracy": 74.87,
"Cost per 1k": 0.29
},
{
"Router Name": "Weave Router",
"Arena Score": 72.82,
Expand All @@ -55,26 +33,37 @@
"Cost per 1k": 0.94
},
{
"Router Name": "OrcaRouter-Adaptive",
"Arena Score": 72.08,
"Router Name": "Nadir Router",
"Arena Score": 72.29,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 22.62,
"Robustness Score": 25.48,
"Latency Score": null,
"Accuracy": 75.54,
"Cost per 1k": 1.0
"Accuracy": 75.01,
"Cost per 1k": 0.68
},
{
"Router Name": "azure",
"Arena Score": 71.87,
"Router Name": "vllm",
"Arena Score": 72.15,
"Optimal Selection Score": 20.77,
"Optimal Cost Score": 17.19,
"Optimal Acc. Score": 90.0,
"Robustness Score": 73.1,
"Latency Score": null,
"Accuracy": 73.19,
"Cost per 1k": 0.23
},
{
"Router Name": "OrcaRouter-Adaptive",
"Arena Score": 72.08,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 71.43,
"Robustness Score": 22.62,
"Latency Score": null,
"Accuracy": 72.82,
"Cost per 1k": 0.22
"Accuracy": 75.54,
"Cost per 1k": 1.0
},
{
"Router Name": "R2-Router",
Expand All @@ -87,6 +76,17 @@
"Accuracy": 71.23,
"Cost per 1k": 0.06
},
{
"Router Name": "azure",
"Arena Score": 70.42,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 71.43,
"Latency Score": null,
"Accuracy": 72.94,
"Cost per 1k": 0.73
},
{
"Router Name": "Auto Router",
"Arena Score": 70.05,
Expand Down
Loading