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

Discriminative Task on RPEval Implicit Memory, Single-Preference

0.02Ignorance Score

Qwen2.5-7B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2.5-7B 2026.01		0.02	0.6	0.52	0.38
GPT-5 2026.01		0.04	0.66	0.68	0.46
GPT-4.1 2026.01		0.08	0.36	0.88	0.44
DeepSeek-V3 2026.01		0.1	0.58	0.6	0.43
GPT-5 + Reminder 2026.01		0.12	0.6	0.76	0.49
Qwen2.5-7B + Reminder 2026.01		0.16	0.71	0.45	0.41
Qwen2.5-7B + CoT 2026.01		0.16	0.89	0.3	0.41
GPT-5 + CoT 2026.01		0.2	0.72	0.7	0.54
GPT-4.1 + Reminder 2026.01		0.24	0.48	0.84	0.52
GPT-4.1 + CoT 2026.01		0.24	0.52	0.96	0.57
DeepSeek-V3 + Reminder 2026.01		0.48	0.79	0.62	0.6
DeepSeek-V3 + CoT 2026.01		0.52	0.7	0.58	0.6
GPT-5 + RP-Reasoner 2026.01		0.54	0.82	0.96	0.77
DeepSeek-V3 + RP-Reasoner 2026.01		0.6	0.7	0.82	0.71
Qwen2.5-7B + RP-Reasoner 2026.01		0.66	0.52	0.5	0.56
GPT-4.1 + RP-Reasoner 2026.01		0.7	0.64	0.9	0.75