Share your thoughts, 1 month free Claude Pro on usSee more

Reasoning on ARC Challenge (Accuracy)

94.3Accuracy

GGRO

Updated 16d ago

Evaluation Results

Method	Links
GGRO 2026.06		94.3
BoN (N=64) 2026.06		92.8
RS 2026.06		92.3
ARGS-G 2026.06		92
CARDS 2026.06		91.8
CBS 2026.06		90.5
SEA 2026.06		87.8
CBS 2026.06		87.5
RS 2026.06		86
BoN (N=64) 2026.06		86
GGRO 2026.06		86
Vanilla LLM 2026.06		84
ARGS-G 2026.06		84
CARDS 2026.06		82.8
Vanilla LLM 2026.06		80
SEA 2026.06		76
FP16 2026.07		62.37
GSRQ 2026.07		59.3
VQLLM 2026.07		57.76
Lizard 2026.07		56.7
STILL (concurrent) 2026.07		56.7
Liger-GLA 2026.07		55.6
LoLa 2026.07		55.4
OURS (GDN) 2026.07		54.92
OURS (GDN) 2026.07		54.86
LLaMA 3.1 8B 2026.07		54.78
Llamba 2026.07		54.6
LolCaT 2026.07		54.44
Llama 3-8B 2026.06		53.1
GSRQ 2026.07		52.05
LLaDA-8B 2026.06		45.9
GSRQ 2026.07		45.22
Llama 2-7B 2026.06		45.1
PivotTrace 2026.06		44.7
Falcon-7B 2026.06		43.2
Sumi-7B 2026.06		43
Entropy 2026.06		41.7
Consistency 2026.06		40.8
OLMo-7B 2026.06		40.3
VQLLM 2026.07		37.03
CoE 2026.06		36.7
Random 2026.06		36.1
Self-Certainty 2026.06		32.7
CoT-Kinetics 2026.06		32.3