Debugging

Shows task share and model composition within a classified request sample. It is not absolute volume or total market demand.

code

Sample requests2.1%

Sample tokens5.7%

Within category19.8%

Category tokens19.6%

TOP MODELS

Model composition

10 models

1
deepseek/deepseek-v4.1-flash-20261017deepseek/deepseek-v4.1-flash-20261017
26.9%req29.9%tok
2
Crouton Alphastealth/crouton-alpha
10.4%req8.0%tok
3
z-ai/glm-5.3-flash-20260826z-ai/glm-5.3-flash-20260826
9.3%req5.6%tok
4
deepseek/deepseek-v4.1-flash-20260910deepseek/deepseek-v4.1-flash-20260910
6.8%req7.9%tok
5
Tencent: Hy4tencent/hy4
3.5%req6.3%tok
6
openai/gpt-6.1-sol-20260929openai/gpt-6.1-sol-20260929
2.7%req3.0%tok
7
openai/gpt-6-luna-20260922openai/gpt-6-luna-20260922
2.4%req1.9%tok
8
z-ai/glm-5.3-20260816z-ai/glm-5.3-20260816
2.3%req2.9%tok
9
anthropic/claude-haiku-5.5-20261007anthropic/claude-haiku-5.5-20261007
2.3%req0.8%tok
10
MoonshotAI: Kimi K3.1 Promoonshotai/kimi-k3.1-pro
1.9%req3.8%tok