SambaNova

qwen2-5-coder-assistant

Sambanova Qwen-2.5-coder-32B coding Assistant

deepseek-r1-assistant

SambaNova assistant using DeepSeek-R1-Distill-Llama-70B and qwen2.5-coder-32b-instruct for autocompletion

Meta-Llama-3.2 3B-Instruct

Meta-Llama-3.1 70B-Instruct

Qwen2.5 Coder-32B-Instruct

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Meta-Llama-3.3 70B-Instruct

Meta-Llama-3.2 90B-Vision-Instruct

Meta-Llama-3.2 1B-Instruct

Meta-Llama-3.2 11B-Vision-Instruct

QwQ 32B-Preview

DeepSeek-R1-Distill-Llama 70B

Meta-Llama-3.1 8B-Instruct

Meta-Llama-3.1 405B-Instruct

Llama-3.1 Tulu-3-405B

Qwen2.5 72B-Instruct

DeepSeek R1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks