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

Selective prediction on Classical Minds metacognitive battery (test)

95Baseline Score

Gemini 3 Flash

Updated 1mo ago

Evaluation Results

Method	Links
Gemini 3 Flash 2026.04		95	53.9	0.004	0.003	0.004
GLM-5 2026.04		94.3	58.7	0.024	0.022	0.023
Gemini 3.1 Pro 2026.04		94.3	52.2	0.007	0.014	0
Gemini 2.5 Flash 2026.04		93.9	57.9	0.016	0.026	0.034
Opus 4.6 2026.04		93.7	61.7	0.018	0.022	0.032
Sonnet 4.6 2026.04		92.7	71.7	0.039	0.04	0.05
Gemini 2.5 Pro 2026.04		92.6	56.1	0.024	0.02	0.017
Qwen 80B Think 2026.04		92.6	51.8	0.024	0.023	0.036
GPT-5.4 2026.04		92.4	64.6	0.033	0.038	0.046
Qwen Coder 480B 2026.04		90.8	68.6	0.032	0.043	0.042
Qwen 235B 2026.04		90.3	64.8	0.035	0.04	0.029
Qwen 80B Inst 2026.04		89.5	58.4	0.024	0.029	0.04
Claude Haiku 4.5 2026.04		89.1	65.7	0.04	0.041	0.044
DeepSeek V3.2 2026.04		88.5	65.1	0.015	0.03	0.057
GPT-5.4 mini 2026.04		88.4	63.3	0.021	0.04	0.048
Gemma 3 27B 2026.04		88	63.1	0.03	0.041	0.04
Gemma 3 12B 2026.04		85.7	61.5	0.029	0.045	0.044
DeepSeek-R1 2026.04		85.3	3.1	0.036	0.06	0.143
GPT-5.4 nano 2026.04		79.6	56.5	0.03	0.049	0.044
Gemma 3 1B 2026.04		60.3	48.3	0.003	0.009	0.126