List your company

Code Generation on MBPP EvalPlus base

90.5Pass@1Claude 3.5 Sonnet
47.8658.937081.07Jul 31, 2024

Evaluation results

MethodLinks
Claude 3.5 Sonnet2024.0790.5
Llama 3 405BParameters=405B2024.0788.6
GPT-4o2024.0787.8
Llama 3 70BParameters=70B2024.0786
GPT-42024.0783.6
GPT-3.5 Turbo2024.0782
Mixtral 8x22BParameters=8x22B2024.0778.6
Llama 3 8BParameters=8B2024.0772.8
Nemotron 4 340BParameters=340B2024.0772.8
Gemma 2 9BParameters=9B2024.0771.7
Mistral 7BParameters=7B2024.0749.5