lcb_codegen_v6: by examples

Results Paper Code


Not solved by any model

There are 36 examples not solved by any model. Solving some of these can be a good signal that your model is indeed better than leading models if these are good problems.
atcoder.abc311_c, atcoder.abc315_e, atcoder.abc319_c, atcoder.abc324_f, atcoder.abc333_e, atcoder.abc343_a, atcoder.abc343_e, atcoder.abc350_c, atcoder.abc350_e, atcoder.abc362_c, atcoder.abc363_f, atcoder.abc373_g, atcoder.abc376_f, atcoder.abc389_g, atcoder.abc397_d, atcoder.arc181_c, atcoder.arc181_d, atcoder.arc182_d, atcoder.arc183_b, atcoder.arc183_d, atcoder.arc184_d, atcoder.arc186_c, atcoder.arc186_e, atcoder.arc188_c, atcoder.arc189_a, atcoder.arc190_a, atcoder.arc190_c, atcoder.arc191_c, atcoder.arc192_b, atcoder.arc193_b, atcoder.arc194_c, atcoder.arc196_a, atcoder.arc196_c, leetcode.3478, leetcode.3527, leetcode.3763

Problems solved by 1 model only

example_link model min_pass1_of_model
atcoder.arc184_c O4-Mini (High) 0.873
leetcode.3701 O3 (High) 0.847
atcoder.abc355_e O3 (High) 0.847
atcoder.arc192_e O3 (High) 0.847
leetcode.3762 O3 (High) 0.847
atcoder.arc183_c O3 (High) 0.847
leetcode.3638 O3 (High) 0.847
atcoder.abc400_g DeepSeek-R1-0528 0.844
atcoder.arc191_a DeepSeek-R1-0528 0.844
atcoder.abc315_f DeepSeek-R1-0528 0.844
atcoder.abc314_e DeepSeek-R1-0528 0.844
atcoder.abc327_e DeepSeek-R1-0528 0.844
atcoder.abc338_f DeepSeek-R1-0528 0.844
atcoder.abc392_d DeepSeek-R1-0528 0.844
atcoder.abc374_d DeepSeek-R1-0528 0.844
atcoder.arc196_d DeepSeek-R1-0528 0.844
atcoder.arc195_d Gemini-2.5-Pro-03-25 0.815
atcoder.arc186_a EXAONE-4.0-32B 0.809
atcoder.abc378_g Grok-3-Mini (High) 0.781
atcoder.abc370_g Grok-3-Mini (High) 0.781
atcoder.abc371_f Grok-3-Mini (High) 0.781
atcoder.abc366_g Grok-3-Mini (High) 0.781
atcoder.abc375_b Grok-3-Mini (High) 0.781
atcoder.arc185_c Grok-3-Mini (High) 0.781
atcoder.abc382_g Grok-3-Mini (High) 0.781
atcoder.abc376_g Grok-3-Mini (High) 0.781
atcoder.abc399_e Grok-3-Mini (High) 0.781
atcoder.arc195_c Grok-3-Mini (High) 0.781
atcoder.abc398_g Grok-3-Mini (High) 0.781
atcoder.abc337_e O3-Mini-2025-01-31 (High) 0.777
leetcode.3613 Gemini-Flash-2.0-Thinking-12-19 0.565

Suspect problems

These are 10 problems with the lowest correlation with the overall evaluation (i.e. better models tend to do worse on these. )

example_link pass1_of_ex tau
atcoder.abc384_f 0.756 -0.278
leetcode.2816 0.970 -0.246
atcoder.abc344_b 0.873 -0.181
atcoder.abc384_g 0.598 -0.176
atcoder.abc367_b 0.991 -0.138
leetcode.3702 0.956 -0.138
leetcode.3613 0.030 -0.123
atcoder.abc389_f 0.547 -0.090
atcoder.abc386_f 0.773 -0.089
atcoder.abc375_a 0.970 -0.077

Histogram of accuracies

Histogram of problems by the accuracy on each problem.

Histogram of difficulties

Histogram of problems by the minimum win rate to solve each problem.