Selective prediction on Classical Minds metacognitive battery (test) benchmark leaderboard · SOTA2 Research

Selective prediction on Classical Minds metacognitive battery (test)

95Baseline ScoreGemini 3 Flash

Evaluation Results

Method	Links
Gemini 3 Flash2026.04		95	53.9	0.004	0.003	0.004
GLM-52026.04		94.3	58.7	0.024	0.022	0.023
Gemini 3.1 Pro2026.04		94.3	52.2	0.007	0.014	0
Gemini 2.5 Flash2026.04		93.9	57.9	0.016	0.026	0.034
Opus 4.62026.04		93.7	61.7	0.018	0.022	0.032
Sonnet 4.62026.04		92.7	71.7	0.039	0.04	0.05
Gemini 2.5 Pro2026.04		92.6	56.1	0.024	0.02	0.017
Qwen 80B Think2026.04		92.6	51.8	0.024	0.023	0.036
GPT-5.42026.04		92.4	64.6	0.033	0.038	0.046
Qwen Coder 480B2026.04		90.8	68.6	0.032	0.043	0.042
Qwen 235B2026.04		90.3	64.8	0.035	0.04	0.029
Qwen 80B Inst2026.04		89.5	58.4	0.024	0.029	0.04
Claude Haiku 4.52026.04		89.1	65.7	0.04	0.041	0.044
DeepSeek V3.22026.04		88.5	65.1	0.015	0.03	0.057
GPT-5.4 mini2026.04		88.4	63.3	0.021	0.04	0.048
Gemma 3 27B2026.04		88	63.1	0.03	0.041	0.04
Gemma 3 12B2026.04		85.7	61.5	0.029	0.045	0.044
DeepSeek-R12026.04		85.3	3.1	0.036	0.06	0.143
GPT-5.4 nano2026.04		79.6	56.5	0.03	0.049	0.044
Gemma 3 1B2026.04		60.3	48.3	0.003	0.009	0.126