Technologies Overview

• BigCodeBench
  Benchmarks & EvaluationTrial
• Claude 3.5 Sonnet
  Frontier ModelsHold
• Claude Opus 4.6
  Frontier ModelsAdopt
• Claude Sonnet 4.6
  Frontier ModelsAdopt
• Cohere Command R/A
  Frontier ModelsAssess
• DeepSeek Coder V2
  Code-Specialized ModelsHold
• DeepSeek R1
  Open Weights ModelsTrial
• DeepSeek V3.1 Terminus
  Open Weights ModelsTrial
• DeepSeek V3.2
  Open Weights ModelsTrial
• Gemini 1.5 Pro
  Frontier ModelsHold
• Gemini 3.1 Pro
  Frontier ModelsTrial
• GLM-4.7-Flash
  Open Weights ModelsTrial
• GLM-5
  Open Weights ModelsTrial
• Google Gemma
  Open Weights ModelsTrial
• GPT-4o
  Frontier ModelsHold
• GPT-5.4
  Frontier ModelsAdopt
• Grok 4.2
  Frontier ModelsTrial
• HumanEval
  Benchmarks & EvaluationHold
• Kimi K2 / K2.5
  Open Weights ModelsTrial
• LiveCodeBench
  Benchmarks & EvaluationTrial
• Llama 3 (Meta)
  Open Weights ModelsHold
• Llama 4 (Meta)
  Open Weights ModelsTrial
• Microsoft Phi
  Open Weights ModelsAssess
• MiniMax M2 / M2.5
  Open Weights ModelsAssess
• Mistral
  Open Weights ModelsTrial
• NVIDIA Nemotron
  Open Weights ModelsAssess
• OpenAI GPT-OSS
  Open Weights ModelsTrial
• Qwen
  Open Weights ModelsTrial
• SWE-bench Verified
  Benchmarks & EvaluationAdopt
• Voyage Code 3
  Code-Specialized ModelsTrial
• Xiaomi MiMo
  Open Weights ModelsAssess