Submission Request* Deus-XM - Dual-Model Consensus System
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
Model Information
- Model Name: Deus-XM
- Type: Dual-model consensus architecture (closed-source)
- API Endpoint: https://solsticestudio.ai/v1/chat/completions
- API Format: OpenAI-compatible
Architecture
Deus-XM combines Gemini 2.0 Flash and Claude Sonnet 4 in a consensus-based
architecture with RAG enhancement via Pinecone vector database.
Self-Reported Benchmark Results
| Benchmark | Score |
|---|---|
| GSM8K | 95.8% |
| TruthfulQA | 89.5% |
| MMLU | 83.0% |
| GPQA | 44.0% |
Request
I request inclusion in Chatbot Arena for community evaluation.
My API is live and supports the OpenAI chat completions format.
I can provide API access for your evaluation infrastructure.
I'm soloing the industry to show everyone a better way.
Contact
justin@solsticestudio.ai
gsm8k_Deus-XM_20251201_231203.json
mmlu_Deus-XM_20251202_031233.json
truthfulqa_Deus-XM_20251202_000212.json
gpqa_Deus-XM_20251202_114551.json
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No repository files, tests, or entry points are identified; start by locating the Chatbot Arena model-submission and evaluation workflow in the Python codebase. Confirm the maintainer's requirements for external model access and define whether completion means a supported integration or an evaluated listing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100