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

Classification on Analysis N-shot

88Accuracy

CRISTAL

Updated 25d ago

Evaluation Results

Method	Links
CRISTAL 2026.06		88	0.81
CRISTAL 2026.06		86	0.79
CRISTAL 2026.06		84	0.75
CRISTAL 2026.06		83	0.74
CRISTAL 2026.06		79	0.67
GPT-4o 2026.06		66	0.49
GPT-4o 2026.06		58	0.41
GPT-4o 2026.06		57	0.39
CRISTAL 2026.06		55	0.29
Deepseek-R1 70B 2026.06		43	0.25
Mistral Nemo 3 2026.06		41	0.02
Mistral Nemo 3 2026.06		41	0.02
Qwen2.5-Coder 32B 2026.06		41	0.03
Qwen2.5-Coder 32B 2026.06		39	-0.01
Mistral Nemo 3 2026.06		39	0
Mistral Nemo 3 2026.06		38	-0.02
Mistral Nemo 3 2026.06		37	-0.06
Mistral Nemo 3 2026.06		37	-0.04
Llama 3.1 8B 2026.06		36	0.01
Llama 3.1 8B 2026.06		35	0
Deepseek-R1 14B 2026.06		35	0.05
Qwen2.5-Coder 32B 2026.06		35	-0.05
Llama 3.1 8B 2026.06		35	-0.01
Llama 3.1 8B 2026.06		35	0
Llama 3.1 8B 2026.06		34	-0.01
Deepseek-R1 70B 2026.06		34	0.12
Deepseek-R1 70B 2026.06		33	0.11
Deepseek-R1 14B 2026.06		32	0.02
Deepseek-R1 70B 2026.06		31	0.06
Llama 3 70B 2026.06		31	0
Llama 3.1 8B 2026.06		31	-0.07
Llama 3 70B 2026.06		30	0.01
Mistral Small 3 2026.06		30	0.03
Qwen2 72B 2026.06		30	0.02
Llama 3 70B 2026.06		30	0.01
Deepseek-R1 14B 2026.06		29	-0.05
Mistral Small 3 2026.06		29	0.02
Qwen2 72B 2026.06		29	0.01
Qwen2 72B 2026.06		29	-0.01
Mistral Small 3 2026.06		29	0.02
Deepseek-R1 70B 2026.06		28	0.05
Llama 3 70B 2026.06		28	-0.03
Mistral Small 3 2026.06		28	-0.01
Mistral Small 3 2026.06		28	-0.01
Deepseek-R1 70B 2026.06		27	0.01
Llama 3 70B 2026.06		26	-0.05
Mistral Small 3 2026.06		26	-0.02
Qwen2 72B 2026.06		26	-0.07
Llama 3 70B 2026.06		25	-0.03