List your company

Question Answering on ARC Challenge (ARC-C)

64.1ARC-C ScoreMARI
32.27640.53848.857.062May 27, 2026

Evaluation results

MethodLinks
MARIModel=Qwen2.5-14B2026.0564.1
ITIModel=Qwen2.5-14B2026.0563.8
ReFTModel=Qwen2.5-14B2026.0563.6
VanillaModel=Qwen2.5-14B2026.0563.4
NL-ITIModel=Qwen2.5-14B2026.0563.3
CAAModel=Qwen2.5-14B2026.0563.1
MARIModel=Qwen2.5-32B2026.0560
ITIModel=Qwen2.5-32B2026.0559.6
ReFTModel=Qwen2.5-32B2026.0559.5
VanillaModel=Qwen2.5-32B2026.0559.3
NL-ITIModel=Qwen2.5-32B2026.0559.2
CAAModel=Qwen2.5-32B2026.0559
MARIModel=Qwen2-7B2026.0552.3
ITIModel=Qwen2-7B2026.0552.2
MARIModel=Llama-3-8B2026.0552.1
ReFTModel=Qwen2-7B2026.0552.1
VanillaModel=Qwen2-7B2026.0551.9
NL-ITIModel=Qwen2-7B2026.0551.8
ITIModel=Llama-3-8B2026.0551.7
ReFTModel=Llama-3-8B2026.0551.6
CAAModel=Qwen2-7B2026.0551.6
VanillaModel=Llama-3-8B2026.0551.4
NL-ITIModel=Llama-3-8B2026.0551.3
CAAModel=Llama-3-8B2026.0551.1
ITIModel=Llama-2-13B2026.0542.9
ReFTModel=Llama-2-13B2026.0542.8
VanillaModel=Llama-2-13B2026.0542.6
NL-ITIModel=Llama-2-13B2026.0542.5
MARIModel=Llama-2-13B2026.0542.4
CAAModel=Llama-2-13B2026.0542.3
ITIModel=Llama-2-7B2026.0534.1
ReFTModel=Llama-2-7B2026.0534
VanillaModel=Llama-2-7B2026.0533.8
NL-ITIModel=Llama-2-7B2026.0533.7
CAAModel=Llama-2-7B2026.0533.5
MARIModel=Llama-2-7B2026.0533.5