Safetensors
qwen3

GenesisGeo Model

📃Paper • 📚 Github📊 Dataset

This model is specialized in automated geometric theorem proving, capable of proposing auxiliary constructions to solve challenging geometry problems. It forms the core of the GenesisGeo project—a neuro-symbolic system that reproduces the AlphaGeometry framework using the Newclid infrastructure.

Developed through large-scale synthetic training, this model demonstrates strong performance in geometric reasoning tasks. It is built upon the Qwen3-0.6B-Base architecture, fine-tuned specifically for generating auxiliary points and constructions in complex proof scenarios.

Model Description

  • Architecture: Transformer-based language model
  • Base Model: Qwen3-0.6B-Base
  • Training Dataset: GenesisGeo Dataset (21.8 million synthetically generated geometric theorems)
  • Purpose: Proposing auxiliary constructions in geometric proofs within a neuro-symbolic reasoning loop

Performance

The integrated neuro-symbolic system achieves:

  • 24/30 problems solved on the IMO-AG-30 benchmark
  • Close to the original AlphaGeometry performance (25/30)

IMO-AG-30_performance

Downloads last month
196
Safetensors
Model size
0.8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ZJUVAI/GenesisGeo

Finetuned
(342)
this model

Dataset used to train ZJUVAI/GenesisGeo

Collection including ZJUVAI/GenesisGeo