List your company

Text-to-code generation on DTVBENCH

10.6Manim ScoreGPT-4o
4.69286.22647.769.2936Oct 27, 2025

Evaluation results

MethodLinks
GPT-4oModel Type=Proprietary2025.1010.64.92
JANUSCODER-8BModel Type=Open-Source, Parameters=8B2025.109.76.07
Qwen2.5-Coder-32B-InsModel Type=Open-Source, Parameters=32B2025.109.614.98
Qwen2.5-Coder-7B-InsModel Type=Open-Source, Parameters=7B2025.108.564.04
JANUSCODER-14BModel Type=Open-Source, Parameters=14B2025.108.415.97
Qwen3-14BModel Type=Open-Source, Parameters=14B2025.106.635.08
Qwen3-8BModel Type=Open-Source, Parameters=8B2025.106.25.18
LLaMA3-8B-InstructModel Type=Open-Source, Parameters=8B2025.104.923.15