MiniMax M2.5 tokens per second
Live benchmark data for MiniMax M2.5 on opencode-go-anthropic. Speed, latency, and reliability — benchmarked every ~10 minutes.
- Latest TPS
- 32.7 tok/s
- 24h avg TPS
- 44.4 tok/s
- TTFT
- 2.2s
- 24h reliability
- 67%
- Last tested
- 9m ago
Tokens per second over time
Time to first token over time
Speed is measured as output tokens ÷ generation time. Each benchmark fires one streaming chat completion with a fixed ~300-token prompt, every ~10 minutes. Full methodology →