AI model rankings
Live LLM rankings based on benchmarks and real routing data from teams using models through SwitchGate. All figures below are placeholder data until the live catalog ships.
Top models
Weekly usage across SwitchGate
Tokens routed per week, stacked by model, over the last twelve months.
LLM leaderboard
The most-routed models this week
Ranked by tokens routed through the gateway over the last seven days.
deepseek-v3.2
by DeepSeek
10.0T tokens
↑191%
gpt-5.2
by OpenAI
9.48T tokens
↑90%
claude-sonnet-4-6
by Anthropic
5.5T tokens
↓21%
gemini-3-flash
by Google
5.03T tokens
↓1%
gpt-5-mini
by OpenAI
4.88T tokens
↑63%
llama-4-scout
by Groq
3.69T tokens
↑28%
mistral-large-3
by Mistral
2.55T tokens
↓14%
grok-4-fast
by xAI
2.46T tokens
↑451%
nova-premier
by AWS Bedrock
2.24T tokens
↓4%
qwen3-235b
by Alibaba
1.76T tokens
↑23%
Placeholder rankings for design purposes; live telemetry ships with the API.
Route to any of them with one line
Every model on this page is one model= string away, behind your budgets and locks.