List your company

Science Question Answering on ARC Challenging (LLMcritic calls, Reduction %)

15.65LLMcritic CallsVecCISC + HAC
10.179611.599813.0214.4402May 8, 2026

Evaluation results

MethodLinks
VecCISC + HACBudget=20, Model=Mistral 7B2026.0515.65-21.73
VecCISC + HACBudget=20, Model=Llama 3.1 8B2026.0514.8-26
VecCISC + HACBudget=20, Model=Llama3.3 70B2026.0513.31-33.43
VecCISC + HACBudget=20, Model=Qwen2.5 7B2026.0510.94-45.3
VecCISC + HACBudget=20, Model=GPT-4o mini2026.0510.39-48.07