List your company

Code Generation on HumanEval-X

67.1Pass@1 (C++)INTERVENOR
5.157621.238837.3253.4012Mar 30, 2023Jun 9, 2023Aug 19, 2023Oct 29, 2023Jan 8, 2024Mar 19, 2024May 29, 2024

Evaluation results

MethodLinks
INTERVENOR2023.1167.1———68.367.1——————————————————
MagicoderS-DSBase Model=DeepSeek-Coder-Base, Parameters=6.7B, Protocol=Zero-shot2024.0563.4———70.766.572.6————————51.8——65—————
AlchemistCoder-DSBase Model=DeepSeek-Coder-Base, Parameters=6.7B, Protocol=Zero-shot2024.0562.2———7268.979.9————————59.8——68.6—————
AlchemistCoder-CLBase Model=CodeLlama-Python, Parameters=7B, Protocol=Zero-shot2024.0553.1———6452.474.4————————42.7——57.3—————
GPT-3.52023.1152.4———50.654.3——————————————————
MagicoderS-CLBase Model=CodeLlama-Python, Parameters=7B, Protocol=Zero-shot2024.0547.6———34.857.968.3————————39.6——49.6—————
DeepSeek-Coder-BaseParameters=6.7B, Protocol=Zero-shot2024.0545.1———56.143.947.6————————38.4——46.2—————
CodeLlama-PythonParameters=7B, Protocol=Zero-shot2024.0533.5———39.635.437.8————————30.5——35.4—————
AlchemistCoder-LBase Model=Llama 2, Parameters=7B, Protocol=Zero-shot2024.0531.1———45.141.556.7————————25.6——37.1—————
CodeLlamaParameters=7B, Protocol=Zero-shot2024.0527.4———25.632.931.7————————12.8——26.1—————
CodeGen2023.1118.1———14.918.4——————————————————
CodeGen-Multi-16BParameters=16B, Type=Multi2023.0318.05———14.9518.419.2234.6455.1730.8450.936.7360.6232.856.4813.0325.4648.7716.7332.0954.39———
CodeGeeX2023.1117.1———2017.6——————————————————
CodeGeeX-13BParameters=13B2023.0317.06———20.0417.5922.8939.5760.9232.215136.758.4232.2856.3314.4325.6847.1418.433.2954.76———
CodeGen-Multi-6BParameters=6B, Type=Multi2023.0311.44———15.1715.4119.4130.2949.6326.2342.8231.7453.9127.9248.819.9823.2641.0114.2827.8947.24———
Llama 2Parameters=7B, Protocol=Zero-shot2024.0511———111414————————6.1——11.2—————
GPT-NeoX-20BParameters=20B2023.039.9———8.8711.2813.8322.7239.5618.9938.7519.5542.2320.7842.67515.732.089.7819.5539.06———
InCoder2023.119.5———9.113——————————————————
InCoder-6.7BParameters=6.7B2023.039.5———9.0512.9816.4126.5543.9519.336.118.6440.722.9843.348.6813.828.3111.3320.2538.48———
GPT-J-6BParameters=6B2023.037.54———7.868.9911.118.6730.9813.6730.1614.3732.9616.3233.774.0110.8123.77.914.7730.32———
ChatGLM-3-6BSampling strategy=Greedy, Note=Baseline2024.02—18.3——————————————————————
Falcon-40BSampling strategy=Greedy, Note=Baseline2024.02—20.7——————————————————————
InternLM-20BSampling strategy=Greedy, Note=Baseline2024.02—21.3——————————————————————
LLaMA-2-13BSampling strategy=Greedy, Note=Baseline2024.02—20.1——————————————————————
LLaMA-2-70BSampling strategy=Greedy, Note=Baseline2024.02—28——————————————————————
LLaMA-2-7BSampling strategy=Greedy, Note=Baseline2024.02—18.9——————————————————————
Qwen-14BSampling strategy=Greedy, Note=Baseline2024.02—26.8——————————————————————
Qwen3-4B + FBS-Full (ours)Backbone=Qwen3-4B2026.01——————————————————46.2——5320.736
SPACEBackbone=ChatGLM-3-6B, Sampling strategy=Greedy2024.02—18.33.342.71————————————————————
SPACEBackbone=LLaMA-2-7B, Sampling strategy=Greedy2024.02—18.93.543.18————————————————————
SPACEBackbone=LLaMA-2-13B, Sampling strategy=Greedy2024.02—20.13.763.43————————————————————
SPACEBackbone=Qwen-14B, Sampling strategy=Greedy2024.02—26.83.513.19————————————————————
SPACEBackbone=InternLM-20B, Sampling strategy=Greedy2024.02—21.33.313.16————————————————————
SPACEBackbone=Falcon-40B, Sampling strategy=Greedy2024.02—20.73.583.58————————————————————
SPACEBackbone=LLaMA-2-70B, Sampling strategy=Greedy2024.02—284.324.04————————————————————