ResearchTasksPython CodingPython CodingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMBPP standard (test)CoT85.25Pass@1 Accuracy32Feb 26, 2026HumanEval-X (test)InternLM2-Chat-7B-SFT43.9Accuracy13Feb 26, 2026HumanEval (test)InternLM2-Chat-20B67.7Accuracy13Feb 26, 2026MBPP-CN v1 (test)InternLM2-20B53.2Pass@113Feb 26, 2026HumanEval-X v1 (test)InternLM2-20B48.2Pass@113Feb 26, 2026HumanEval v1 (test)InternLM2-7B56.1Pass@113Feb 26, 2026