Models
Claude Haiku 3.5
apianthropic
Anthropic: claude-3-5-haiku-20241022
Context: 200,000 tokens
Claude Opus 4
apiAnthropic
Anthropic most capable model
Context: 200,000 tokens
Claude Sonnet 4
apianthropic
Anthropic: claude-sonnet-4-20250514
Context: 200,000 tokens
CodeLlama 7B
localollama
Ollama: codellama:7b
Context: 4,096 tokens
Gemini 2.0 Flash
apiGoogle fast model
Context: 1,000,000 tokens
Gemini 2.5 Flash
apiGoogle: gemini-2.5-flash
Context: 8,192 tokens
Gemini 2.5 Pro
apiGoogle most capable model
Context: 1,048,576 tokens
Gemma 2 2B
localollama
Ollama: gemma2:2b
Context: 4,096 tokens
Gemma 3n E4B (LM Studio)
locallmstudio
LM Studio: google/gemma-3n-e4b
Context: 4,096 tokens
GPT-4.1
apiOpenAI
OpenAI latest flagship model
Context: 1,047,576 tokens
GPT-4.1 Mini
apiopenai
OpenAI: gpt-4.1-mini
Context: 8,192 tokens
GPT-4o
apiopenai
OpenAI flagship model
Context: 128,000 tokens
GPT-4o Mini
apiopenai
OpenAI lightweight model
Context: 128,000 tokens
Llama 3 70B
localmeta
Local LLM baseline
Context: 8,192 tokens
Llama 3.2 1B (LM Studio)
locallmstudio
LM Studio: llama-3.2-1b-instruct
Context: 4,096 tokens
Llama 3.2 3B
localollama
Ollama: llama3.2:3b
Context: 4,096 tokens
Phi-3 Mini
localollama
Ollama: phi3:mini
Context: 4,096 tokens