---
title: TuRTLe Leaderboard
emoji: 🐢
colorFrom: gray
colorTo: green
sdk: docker
app_port: 7860
pinned: true
license: apache-2.0
short_description: A Unified Evaluation of LLMs for RTL Generation.
models:
  - ByteDance-Seed/Seed-Coder-8B-Instruct
  - ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
  - ByteDance-Seed/Seed-OSS-36B-Instruct
  - HuggingFaceH4/starchat2-15b-v0.1
  - Multilingual-Multimodal-NLP/IndustrialCoder
  - Multilingual-Multimodal-NLP/IndustrialCoder-Thinking
  - NousResearch/Hermes-4-14B
  - Qwen/QwQ-32B
  - Qwen/Qwen2.5-14B-Instruct
  - Qwen/Qwen2.5-14B-Instruct-1M
  - Qwen/Qwen2.5-32B
  - Qwen/Qwen2.5-72B-Instruct
  - Qwen/Qwen2.5-7B-Instruct
  - Qwen/Qwen2.5-Coder-14B-Instruct
  - Qwen/Qwen2.5-Coder-32B-Instruct
  - Qwen/Qwen2.5-Coder-7B-Instruct
  - Qwen/Qwen3-235B-A22B
  - Qwen/Qwen3-8B
  - Qwen/Qwen3-Coder-480B-A35B-Instruct
  - RedHatAI/Meta-Llama-3.1-405B-FP8
  - agentica-org/DeepCoder-14B-Preview
  - codellama/CodeLlama-70b-hf
  - deepseek-ai/DeepSeek-R1
  - deepseek-ai/DeepSeek-R1-0528
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - deepseek-ai/DeepSeek-V3.1-Terminus
  - deepseek-ai/deepseek-coder-33b-instruct
  - deepseek-ai/deepseek-coder-6.7b-instruct
  - henryen/OriGen
  - infly/OpenCoder-8B-Instruct
  - ishorn5/RTLCoder-Deepseek-v1.1
  - ishorn5/RTLCoder-v1.1
  - meta-llama/Llama-3.3-70B-Instruct
  - mistralai/Magistral-Small-2506
  - moonshotai/Kimi-K2-Instruct-0905
  - moonshotai/Kimi-K2.5
  - openai/gpt-oss-120b
  - openai/gpt-oss-20b
  - yang-z/CodeV-CL-7B
  - yang-z/CodeV-DS-6.7B
  - yang-z/CodeV-QW-7B
  - yangyiyao/HaVen-CodeQwen
  - zai-org/GLM-5-FP8
  - zhuyaoyu/CodeV-R1-Distill-Qwen-7B
  - google/gemma-4-31B-it
---

# TuRTLe Leaderboard

A unified evaluation leaderboard for Large Language Models on RTL (Register Transfer Level) code generation tasks.

This space serves pre-built static files from the `dist/` folder.

## License

This project is licensed under the Apache License 2.0.
See the [LICENSE](./LICENSE) and [NOTICE](./NOTICE) files for more details.