AI Model Speed Rankings

Models ranked by measured output throughput (tokens per second) and average latency.

  1. Z.ai GLM 5.2 — Throughput: 103.0 tps, Latency: 3465.34s
  2. OpenAI GPT-5.6 Terra — Throughput: 45.7 tps, Latency: 709.92s
  3. OpenAI GPT-5.5 — Throughput: 45.2 tps, Latency: 0.00s
  4. OpenAI gpt-5.4 — Throughput: 44.9 tps, Latency: 872.21s
  5. OpenAI GPT-5.6 Sol — Throughput: 37.6 tps, Latency: 1638.11s
  6. OpenAI GPT-5.6 Luna — Throughput: 36.5 tps, Latency: 545.00s
  7. Z.ai GLM 4.7 Flash — Throughput: 16.5 tps, Latency: 0.00s
  8. OpenAI GPT Image 2 — Throughput: 12.0 tps, Latency: 19163.00s