Duplicated from open-agent-leaderboard/openai-solo

Exgentic
/

openai-solo

agent-evaluation

Model card Files Files and versions

OpenAI Solo

This is a tracking repo for OpenAI Solo, used by the Open Agent Leaderboard to report evaluation results on HuggingFace.

OpenAI's Agent SDK for building single-agent workflows with tool use and structured outputs.

Framework: openai-agents-python
Leaderboard: Open Agent Leaderboard
Paper: arXiv:2602.22953

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for Exgentic/openai-solo

General Agent Evaluation

Paper • 2602.22953 • Published Feb 26 • 12

Evaluation results

Overall
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Claude Opus 4.5
0.73 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: DeepSeek V3.2
0.32 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: GPT-5.2
0.39 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Kimi K2.5
0.25 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Gemini 3 Pro
0.59 ^*
Appworld
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Claude Opus 4.5
0.68 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: DeepSeek V3.2
0.06 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: GPT-5.2
0 ^*