Skip to content
34 changes: 17 additions & 17 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -32,23 +32,23 @@ RouterArena bridges this gap by providing an open evaluation platform and benchm

For more details, please see our [website](https://routeworks.github.io/leaderboard) and [blog](https://huggingface.co/blog/JerryPotter/who-routes-the-routers).

| Rank | Router | Affiliation | Arena | Opt.Sel | Opt.Cost | Opt.Acc | Lat | Robust |
|------|---------|--------------|--------|------------|-----------|----------|----------|-------------|
| 🥇 | MIRT-BERT | 🎓 USTC | 66.89 | 3.44 | 19.62 | 78.18 | 27.03 | 94.50 |
| 🥈 | Azure | 💼 Microsoft | 66.66 | 22.52 | 46.32 | 81.96 | — | — |
| 🥉 | NIRT-BERT | 🎓 USTC | 66.12 | 3.83 | 14.04 | 77.88 | 10.42 | 44.50 |
| 4 | GPT-5 | 💼 OpenAI | 64.32 | — | — | — | — | — |
| 5 | vLLM-SR | 💼 vLLM | 64.32 | 4.79 | 12.54 | 79.33 | 0.19 | 100.00 |
| 6 | CARROT | 🎓 UMich | 63.87 | 2.68 | 6.77 | 78.63 | 1.50 | 93.60 |
| 7 | Chayan | 💼 Adaptive Classifier | 63.83 | 43.03 | 43.75 | 88.74 | — | — |
| 8 | NotDiamond | 💼 NotDiamond | 63.00 | 1.55 | 2.14 | 76.81 | — | — |
| 9 | MLP | 🎓 Academic | 57.56 | 13.39 | 24.45 | 83.32 | 90.91 | 96.90 |
| 10 | GraphRouter | 🎓 UIUC | 57.22 | 4.73 | 38.33 | 74.25 | 2.70 | 97.50 |
| 11 | KNN | 🎓 Academic | 55.48 | 13.09 | 25.49 | 78.77 | 1.33 | 51.30 |
| 12 | RouteLLM | 🎓 Berkeley | 48.07 | 99.72 | 99.63 | 68.76 | 0.40 | 99.80 |
| 13 | RouterDC | 🎓 SUSTech | 33.75 | 39.84 | 73.00 | 49.05 | 10.75 | 97.60 |

🎓 Academic  💼 Commercial
| Rank | Router | Affiliation | Arena | Optimal Selection | Optimal Cost | Optimal Accuracy | Latency | Robustness |
|------|--------------------|-----------------------------|--------|-----------------|--------------|----------------|---------|------------|
| 🥇 | [MIRTBERT](https://arxiv.org/pdf/2506.01048) [[GH]](https://github.com/Mercidaiha/IRT-Router) | 🎓 USTC | 66.89 | 3.44 | 19.62 | 78.18 | 27.03 | 94.50 |
| 🥈 | [Azure‑Router](https://ai.azure.com/catalog/models/model-router) [[Web]](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/model-router) | 💼 Microsoft | 66.66 | 22.52 | 46.32 | 81.96 | — | — |
| 🥉 | [NIRTBERT](https://arxiv.org/pdf/2506.01048) [[GH]](https://github.com/Mercidaiha/IRT-Router) | 🎓 USTC | 66.12 | 3.83 | 14.04 | 77.88 | 10.42 | 44.50 |
| 4 | [GPT‑5](https://openai.com/index/introducing-gpt-5/)| 💼 OpenAI | 64.32 | — | — | — | — | — |
| 5 | [vLLM‑SR](https://vllm-semantic-router.com/) [[GH]](https://github.com/vllm-project/semantic-router) [[HF]](https://huggingface.co/llm-semantic-router) | 💼 vLLM | 64.32 | 4.79 | 12.54 | 79.33 | 0.19 | 100.00 |
| 6 | [CARROT](https://arxiv.org/abs/2502.03261) [[GH]](https://github.com/somerstep/CARROT) [[HF]](https://huggingface.co/CARROT-LLM-Routing) | 🎓 UMich | 63.87 | 2.68 | 6.77 | 78.63 | 1.50 | 93.60 |
| 7 | [Chayan](https://huggingface.co/adaptive-classifier/chayan) [[HF]](https://huggingface.co/adaptive-classifier/chayan) | 🎓 Adaptive Classifier | 63.83 | 43.03 | 43.75 | 88.74 | — | — |
| 8 | [NotDiamond](https://www.notdiamond.ai/) | 💼 NotDiamond | 63.00 | 1.55 | 2.14 | 76.81 | — | — |
| 9 | [RouterBench‑MLP](https://arxiv.org/pdf/2403.12031) [[GH]](https://github.com/withmartian/routerbench) [[HF]](https://huggingface.co/datasets/withmartian/routerbench) | 🎓 Martian | 57.56 | 13.39 | 24.45 | 83.32 | 90.91 | 96.90 |
| 10 | [GraphRouter](https://arxiv.org/abs/2410.03834) [[GH]](https://github.com/ulab-uiuc/GraphRouter) | 🎓 UIUC | 57.22 | 4.73 | 38.33 | 74.25 | 2.70 | 97.50 |
| 11 | [RouterBench‑KNN](https://arxiv.org/pdf/2403.12031) [[GH]](https://github.com/withmartian/routerbench) [[HF]](https://huggingface.co/datasets/withmartian/routerbench) | 🎓 Martian | 55.48 | 13.09 | 25.49 | 78.77 | 1.33 | 51.30 |
| 12 | [RouteLLM](https://arxiv.org/abs/2406.18665) [[GH]](https://github.com/lm-sys/RouteLLM) [[HF]](https://huggingface.co/routellm) | 🎓 Berkeley | 48.07 | 99.72 | 99.63 | 68.76 | 0.40 | 99.80 |
| 13 | [RouterDC](https://arxiv.org/abs/2409.19886) [[GH]](https://github.com/shuhao02/RouterDC) | 🎓 SUSTech | 33.75 | 39.84 | 73.00 | 49.05 | 10.75 | 97.60 |

🎓 Open-source  💼 Closed-source

<!-- <p align="center">
<img src="images/leaderboard.png" alt="Make GPU Sharing Flexible and Easy" width="500" />
Expand Down