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

Code Generation on Code Category Average (test)

77.43Accuracy

Instruct Model

Updated 1mo ago

Evaluation Results

Method	Links
Instruct Model 2026.03		77.43	0.57	0.22	0.23
CoCA 2026.03		76.6	0.72	0.16	0.19
RLVR+QuestionProb 2026.03		76.58	0.47	0.7	0.68
RLVR+Assessor Model 2026.03		76.58	0.55	0.29	0.3
RLVR+Probe 2026.03		76.58	0.62	0.71	0.68
RLVR 2026.03		76.1	0.55	0.23	0.23
RLVR+QuestionProb 2026.03		69.03	0.42	0.65	0.63
RLVR+Assessor Model 2026.03		69.03	0.64	0.29	0.33
RLVR+Probe 2026.03		69.03	0.59	0.37	0.39
CoCA 2026.03		67.38	0.67	0.28	0.3
Instruct Model 2026.03		63.78	0.52	0.3	0.33
RLVR+QuestionProb 2026.03		57.15	0.46	0.48	0.48
RLVR+Assessor Model 2026.03		57.15	0.63	0.25	0.35
RLVR+Probe 2026.03		57.15	0.64	0.27	0.34
Instruct Model 2026.03		55.1	0.53	0.41	0.42
CoCA 2026.03		46.72	0.72	0.09	0.22
RLVR 2026.03		39	0.58	0.56	0.55
RLVR 2026.03		34.58	0.48	0.56	0.54