AI Model Speed Rankings

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

  1. Z.ai GLM 5.2 — Throughput: 110.5 tps, Latency: 5044.35s
  2. OpenAI gpt-5.6-luna — Throughput: 51.1 tps, Latency: 1273.00s
  3. OpenAI GPT-5.5 — Throughput: 46.6 tps, Latency: 0.00s
  4. OpenAI GPT-5.6 Terra — Throughput: 46.5 tps, Latency: 1145.62s
  5. OpenAI GPT-5.6 Sol — Throughput: 29.4 tps, Latency: 1263.62s
  6. Z.ai GLM 4.7 Flash — Throughput: 23.3 tps, Latency: 0.00s
  7. OpenAI GPT-6 Astra — Throughput: 13.9 tps, Latency: 1019.00s
  8. OpenAI GPT Image 2 — Throughput: 6.6 tps, Latency: 26499.41s