Add TemuClaude to Chatbot Arena — OpenAI-compatible API endpoint #3899

Model Submission: TemuClaude

I'd like to add TemuClaude to the Chatbot Arena for blind testing.

API Details

• Endpoint: https://saifulbusiness47--temuclaude-serve.modal.run/v1/chat/completions
• Format: OpenAI-compatible Chat Completions API
• Method: POST
• No API key required (open access for evaluation)
• Health check: GET https://saifulbusiness47--temuclaude-serve.modal.run/health
• Model list: GET https://saifulbusiness47--temuclaude-serve.modal.run/v1/models
• Model name: temuclaude

About TemuClaude

TemuClaude is a multi-model orchestration pipeline — not a single model. It routes queries across 8 models based on difficulty:

1. Trivial queries → cheapest model (Hy3 Preview)
2. Medium queries → specialist routing (DeepSeek for math, MiniMax for creative, MiMo for multimodal)
3. Hard queries → full Mixture-of-Agents pipeline:
   • 3 models propose in parallel (GLM-5.2 + DeepSeek V4 Pro + Gemini 3.5 Flash)
   • Aggregation by GLM-5.2 (consensus analysis, contradiction resolution)
   • QA gate scoring by Nemotron (5-rubric, independent judge)
   • Reflexion retry if QA < 8 (DeepSeek with feedback)
   • Frontier fallback if QA < 6 (Claude Sonnet 5)
   • Self-consistency for math (3 samples, majority vote)

Test Command

curl -X POST https://saifulbusiness47--temuclaude-serve.modal.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"temuclaude","messages":[{"role":"user","content":"What is the capital of France?"}]}'

Hosting

Hosted on Modal (serverless, auto-scaling). Max duration 120s per request. Timeout safeguard at 45s with single-model fallback.

The endpoint is live and ready for integration.

Contact: saifulbusiness47@gmail.com