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
1,682 changes: 1,682 additions & 0 deletions src/data/flip_labels/flip_labels_asiainfo.json

Large diffs are not rendered by default.

422 changes: 211 additions & 211 deletions src/data/flip_labels/flip_labels_barouter.json

Large diffs are not rendered by default.

1,682 changes: 1,682 additions & 0 deletions src/data/flip_labels/flip_labels_divyam.json

Large diffs are not rendered by default.

1,682 changes: 1,682 additions & 0 deletions src/data/flip_labels/flip_labels_nadir-caliper.json

Large diffs are not rendered by default.

1,682 changes: 1,682 additions & 0 deletions src/data/flip_labels/flip_labels_paix2.json

Large diffs are not rendered by default.

406 changes: 203 additions & 203 deletions src/data/flip_labels/flip_labels_sqwish-router.json

Large diffs are not rendered by default.

8,820 changes: 6,274 additions & 2,546 deletions src/data/routerMetrics/category_scores.json

Large diffs are not rendered by default.

106 changes: 75 additions & 31 deletions src/data/routerMetrics/leaderboard.json
Original file line number Diff line number Diff line change
@@ -1,47 +1,80 @@
[
{
"Router Name": "Paix2",
"Arena Score": 77.63,
"Optimal Selection Score": 89.67,
"Optimal Cost Score": 62.92,
"Optimal Acc. Score": 100.0,
"Robustness Score": 77.86,
"Latency Score": null,
"Accuracy": 79.69,
"Cost per 1k": 0.27
},
{
"Router Name": "Sqwish Router",
"Arena Score": 76.21,
"Optimal Selection Score": 9.04,
"Optimal Cost Score": 23.49,
"Optimal Acc. Score": 94.07,
"Robustness Score": 51.67,
"Latency Score": null,
"Accuracy": 79.76,
"Cost per 1k": 0.7
},
{
"Router Name": "Divyam",
"Arena Score": 75.85,
"Optimal Selection Score": 4.93,
"Optimal Cost Score": 16.03,
"Optimal Acc. Score": 93.43,
"Robustness Score": 98.33,
"Latency Score": null,
"Accuracy": 78.59,
"Cost per 1k": 0.48
},
{
"Router Name": "Cross-Router",
"Arena Score": 76.12,
"Arena Score": 75.75,
"Optimal Selection Score": 17.66,
"Optimal Cost Score": 45.49,
"Optimal Acc. Score": 90.31,
"Robustness Score": 67.14,
"Latency Score": null,
"Accuracy": 78.14,
"Cost per 1k": 0.3
"Cost per 1k": 0.4
},
{
"Router Name": "Nadir-Tumbler",
"Arena Score": 75.17,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 66.43,
"Latency Score": null,
"Accuracy": 75.34,
"Cost per 1k": 0.08
},
{
"Router Name": "vllm",
"Arena Score": 75.3,
"Arena Score": 74.86,
"Optimal Selection Score": 16.81,
"Optimal Cost Score": 25.1,
"Optimal Acc. Score": 89.37,
"Robustness Score": 67.62,
"Latency Score": null,
"Accuracy": 77.18,
"Cost per 1k": 0.3
"Cost per 1k": 0.42
},
{
"Router Name": "Sqwish Router",
"Arena Score": 75.27,
"Optimal Selection Score": 7.41,
"Optimal Cost Score": 25.1,
"Optimal Acc. Score": 90.47,
"Robustness Score": 100.0,
"Latency Score": null,
"Accuracy": 76.4,
"Cost per 1k": 0.18
},
{
"Router Name": "Nadir-Tumbler",
"Arena Score": 75.17,
"Router Name": "nadir-caliper",
"Arena Score": 74.55,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 66.43,
"Robustness Score": 79.76,
"Latency Score": null,
"Accuracy": 75.34,
"Cost per 1k": 0.08
"Accuracy": 75.84,
"Cost per 1k": 0.22
},
{
"Router Name": "AgentForge Router",
Expand All @@ -54,6 +87,17 @@
"Accuracy": 74.72,
"Cost per 1k": 0.13
},
{
"Router Name": "BARouter",
"Arena Score": 73.79,
"Optimal Selection Score": 64.41,
"Optimal Cost Score": 67.13,
"Optimal Acc. Score": 93.84,
"Robustness Score": 68.81,
"Latency Score": null,
"Accuracy": 75.72,
"Cost per 1k": 0.36
},
{
"Router Name": "Weave Router",
"Arena Score": 72.82,
Expand Down Expand Up @@ -164,17 +208,6 @@
"Accuracy": 68.41,
"Cost per 1k": 0.29
},
{
"Router Name": "BARouter",
"Arena Score": 67.09,
"Optimal Selection Score": 58.56,
"Optimal Cost Score": 59.03,
"Optimal Acc. Score": 87.91,
"Robustness Score": 52.38,
"Latency Score": null,
"Accuracy": 68.8,
"Cost per 1k": 0.63
},
{
"Router Name": "mirt_bert",
"Arena Score": 66.89,
Expand All @@ -197,6 +230,17 @@
"Accuracy": 66.34,
"Cost per 1k": 0.21
},
{
"Router Name": "AsiaInfo-Router",
"Arena Score": 65.87,
"Optimal Selection Score": null,
"Optimal Cost Score": null,
"Optimal Acc. Score": null,
"Robustness Score": 69.52,
"Latency Score": null,
"Accuracy": 75.2,
"Cost per 1k": 8.54
},
{
"Router Name": "gpt5",
"Arena Score": 64.32,
Expand Down
50 changes: 50 additions & 0 deletions src/data/routers.json
Original file line number Diff line number Diff line change
Expand Up @@ -486,5 +486,55 @@
"qwen/qwen3-235b-a22b-2507",
"z-ai/glm-4.7"
]
},
"nadir-caliper": {
"name": "nadir-caliper",
"affiliation": "@doramirdor",
"githubUrl": "https://github.com/doramirdor",
"type": "open-source",
"description": "Submitted by @doramirdor.",
"modelPool": [
"qwen/qwen3-235b-a22b-2507",
"google/gemini-3.1-flash-lite",
"grok-4.3",
"deepseek/deepseek-v3.2"
]
},
"Paix2": {
"name": "Paix2",
"affiliation": "@xufan866",
"githubUrl": "https://github.com/xufan866",
"type": "open-source",
"description": "Submitted by @xufan866.",
"modelPool": [
"MiniMax-M3",
"agnes-2.0-flash",
"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"THUDM/GLM-4-9B-0414"
]
},
"Divyam": {
"name": "Divyam",
"affiliation": "@samikd",
"githubUrl": "https://github.com/samikd",
"type": "open-source",
"description": "Submitted by @samikd.",
"modelPool": [
"qwen/qwen3-235b-a22b-2507",
"Qwen/Qwen3-Coder-Next",
"gemini-3-flash-preview",
"google/gemini-3.1-flash-lite"
]
},
"AsiaInfo-Router": {
"name": "AsiaInfo-Router",
"affiliation": "@Uncle-LL",
"githubUrl": "https://github.com/Uncle-LL",
"type": "open-source",
"description": "Submitted by @Uncle-LL.",
"modelPool": [
"claude-opus-4-7",
"deepseek/deepseek-v4-flash"
]
}
}
Loading