List your company

Abstract and compositional reasoning on ARC-AGI 2 (test)

51Accuracy (ARC-AGI 2 Test)EvoX
40.643.34648.7Feb 26, 2026

Evaluation results

MethodLinks
EvoXBackbone=Gemini-3-Pro, Inference budget=30 LLM iterations2026.0251
EvoXBackbone=GPT-5, Inference budget=30 LLM iterations2026.0248
OpenEvolveBackbone=Gemini-3-Pro, Inference budget=30 LLM iterations2026.0245
OpenEvolveBackbone=GPT-5, Inference budget=30 LLM iterations2026.0241