Code Arena🏆WebDev
View overall rankings across AI models on agentic coding tasks involving multi-step reasoning and tool use.
Apr 19, 2026
245,610 votes
62 models
Pareto Frontier
CtrlScroll
Pareto Optimal Models
Top performers for their cost
View overall rankings across AI models on agentic coding tasks involving multi-step reasoning and tool use.
Model performance at each price point
Top performers for their cost
claude-opus-4-7
Anthropic · Proprietary
1567
$20/M
glm-5.1
Z.ai · MIT
1536
$2.89/M
qwen3.6-plus
Alibaba · Proprietary
1476
$1.54/M
glm-4.7
Z.ai · MIT
1440
$1.40/M
minimax-m2.7
MiniMax · Modified MIT
1416
$0.97/M
minimax-m2.1-preview
MiniMax · MIT
1392
$0.78/M
deepseek-v3.2-thinking
DeepSeek · MIT
1368
$0.35/M
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1337
$0.24/M