Monthly LLM Rankings

Based on performance, usability, and innovation this month

RankingModelLM Arena ScoreFeaturesModel AvailabilityAPI InputAPI OutputContext WindowTraining Cutoff
Large models
1Claude 3.5 Sonnet1283
  • Image input
  • Canvas
  • Tone selection
api$3.00$15.00200k tokensApr 2024
2GPT-4o1285
  • Canvas
  • Internet Search
  • Image inputs
  • Image creation
  • Voice input
api$5.00$15.00128k tokensOct 2023
3DeepSeek V31317
  • Internet Search
  • Image inputs
both$0.27$1.10~128k tokensJul 2024
4Qwen 2.5 Max1332
  • Canvas
  • Image input
  • Image output
  • Video Generation
  • Internet Search
api$1.60$6.40128k tokensNot specified
5Grok 21288
  • Image input
  • Image output
  • Internet Search
  • Custom Instructions
api$5.00$15.00128k tokensUnknown
6Mistral Large1245
  • Canvas
  • Image input
  • Image output
  • Internet Search
api$2.00$6.0032k tokensUnknown
Thinking Models
1OpenAI o3-mini1310
  • Chain-of-thought
  • Multi-step reasoning
  • Research synthesis
  • Complex analysis
api$1.10$4.40200k tokensOct 2023
2OpenAI o11351
  • Self-reflection
  • Meta-learning
  • Reasoning transparency
  • Knowledge synthesis
api$15.00$60.00200k tokensOct 2023
3DeepSeek R11362
  • Chain-of-thought
  • Multi-step reasoning
  • Research synthesis
  • Complex analysis
both$0.55$2.1964k tokensNot specified
Smaller Models
1GPT-4o Mini1273
  • Text generation
  • Basic chat
  • Simple tasks
api$0.15$0.60128k tokensOct 2023
2Claude 3.5 Haiku1236
  • Quick responses
  • Basic analysis
  • Short-form content
api$0.80$4.00200k tokensJul 2024
3Gemini Flash 2.01357
  • Text generation
  • Basic chat
  • Simple tasks
api$0.10$0.402M tokensNot specified (latest model, likely 2024)

Last updated: 8.2.2025