HEAD-TO-HEAD MODEL ARENA

Claude 3.5 Sonnet vs GPT-4o (Omni)

Side-by-side benchmark differential across coding SWE-bench, human battle Arena ELO, throughput, and API token spend.

Claude 3.5 Sonnet

Anthropic

  • 🏆 Arena Elo: 1335 pts
  • 💻 SWE-bench: 93.7/100
  • 🤖 Agentic: 92/100
  • 💵 Input: $3.00/1M
  • 💵 Output: $15.00/1M

GPT-4o (Omni)

OpenAI

  • 🏆 Arena Elo: 1330 pts
  • 💻 SWE-bench: 90.2/100
  • 🤖 Agentic: 88.5/100
  • 💵 Input: $2.50/1M
  • 💵 Output: $10.00/1M