Skip to content

Add OVA (ova-debate) as API-based model endpoint for Chatbot Arena #3781

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

Open
jacobrlutz wants to merge 1 commit into
base: main
Choose a base branch
from
+26 −0
Open

Add OVA (ova-debate) as API-based model endpoint for Chatbot Arena #3781

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
15 changes: 15 additions & 0 deletions api_endpoints.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
{
"ova-debate": {
"model_name": "ova-debate",
"api_type": "openai",
"api_base": "https://ovamind-production.up.railway.app/api/v1",
"api_key": "sk_ova_arena_lmarena2026",
"anony_only": false,
"recommended_config": {
"temperature": 0.3,
"top_p": 1.0
},
"text-arena": true,
"vision-arena": false
}
}
11 changes: 11 additions & 0 deletions fastchat/model/model_registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1000,3 +1000,14 @@ def get_model_info(name: str) -> ModelInfo:
"https://huggingface.co/cllm",
"consistency-llm is a new generation of parallel decoder LLMs with fast generation speed.",
)

# ── OVA (Multi-Model Debate) ─────────────────────────────────────────────────
register_model_info(
["ova-debate", "ova-arena"],
"OVA (Multi-Model Debate)",
"https://ovamind.ai",
"OVA is a meta-reasoning system that runs structured multi-agent debate "
"across Claude, GPT, Grok, Gemini, and Perplexity before synthesizing a "
"final answer. Confidence-adaptive: 3 rounds for standard queries, up to 9 "
"rounds with axiom decomposition and frame-breaking for hard problems.",
)