AI Model Speed Rankings

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

  1. Moonshot Kimi K2.5 — Throughput: 916.7 tps, Latency: 983.50s
  2. OpenAI gpt-5-nano — Throughput: 624.9 tps, Latency: 24240.08s
  3. xAI Grok 4.20 Multi-Agent — Throughput: 358.8 tps, Latency: 0.00s
  4. Google Gemini 3.1 Flash-Lite — Throughput: 343.8 tps, Latency: 1060.45s
  5. Google gemini-2.5-pro — Throughput: 275.7 tps, Latency: 26226.97s
  6. Google Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) — Throughput: 260.0 tps, Latency: 5625.92s
  7. Google Nano Banana (Gemini 2.5 Flash Image 🍌) — Throughput: 247.2 tps, Latency: 8021.00s
  8. Google Gemini 3.1 Pro Preview — Throughput: 237.9 tps, Latency: 29535.64s
  9. OpenAI GPT-5.6 Luna — Throughput: 222.2 tps, Latency: 3591.84s
  10. OpenAI GPT-5 — Throughput: 211.3 tps, Latency: 22619.39s
  11. Google Gemini 3.5 Flash — Throughput: 200.3 tps, Latency: 7725.31s
  12. Google Gemini 3 Flash Preview — Throughput: 199.6 tps, Latency: 7603.31s
  13. Google gemini-2.5-flash — Throughput: 178.0 tps, Latency: 17261.88s
  14. xAI Grok 4.20 — Throughput: 148.0 tps, Latency: 696.00s
  15. xAI Grok 4.20 (Non-Reasoning) — Throughput: 145.6 tps, Latency: 0.00s
  16. OpenAI gpt-4o-all — Throughput: 137.1 tps, Latency: 4958.33s
  17. xAI Grok 4.5 — Throughput: 126.2 tps, Latency: 5538.48s
  18. OpenAI GPT-5.6 Terra — Throughput: 121.5 tps, Latency: 4571.65s
  19. xAI grok-3-mini — Throughput: 113.8 tps, Latency: 0.00s
  20. Google Gemini 3.1 Pro Preview Customtools — Throughput: 113.5 tps, Latency: 0.00s
  21. OpenAI GPT-5.3 Codex — Throughput: 113.3 tps, Latency: 4485.00s
  22. xAI grok-4-1-fast-reasoning — Throughput: 112.2 tps, Latency: 0.00s
  23. DeepSeek deepseek-chat — Throughput: 110.8 tps, Latency: 0.00s
  24. xAI Grok 4.3 — Throughput: 106.0 tps, Latency: 1363.63s
  25. xAI grok-4-0709 — Throughput: 104.2 tps, Latency: 1038.75s
  26. OpenAI dall-e-3 — Throughput: 103.5 tps, Latency: 60377.00s
  27. OpenAI GPT Image 1.5 — Throughput: 103.2 tps, Latency: 44204.00s
  28. xAI grok-4-1-fast-non-reasoning — Throughput: 101.6 tps, Latency: 788.64s
  29. xAI Grok Build 0.1 — Throughput: 99.8 tps, Latency: 2197.00s
  30. OpenAI Chat Latest (GPT-5.5 Instant) — Throughput: 98.8 tps, Latency: 0.00s
  31. Alibaba qwen-plus — Throughput: 92.3 tps, Latency: 1138.71s
  32. Moonshot Kimi K2.6 — Throughput: 85.2 tps, Latency: 773.50s
  33. OpenAI GPT Image 1.0 — Throughput: 84.9 tps, Latency: 48977.00s
  34. OpenAI gpt-4-all — Throughput: 84.4 tps, Latency: 5470.56s
  35. OpenAI gpt-4-gizmo-* — Throughput: 80.5 tps, Latency: 4098.12s
  36. Z.ai GLM 5.1 — Throughput: 78.4 tps, Latency: 524.50s
  37. OpenAI gpt-4.1-mini — Throughput: 76.5 tps, Latency: 903.86s
  38. OpenAI gpt-5.1-codex-mini — Throughput: 76.4 tps, Latency: 760.50s
  39. OpenAI GPT‑5.3 Instant — Throughput: 74.9 tps, Latency: 1262.00s
  40. OpenAI o4-mini — Throughput: 74.6 tps, Latency: 5126.50s
  41. ByteDance Doubao-Seed-2.0-mini — Throughput: 73.9 tps, Latency: 0.00s
  42. OpenAI gpt-4o-image — Throughput: 72.7 tps, Latency: 36870.00s
  43. OpenAI GPT-5.4 — Throughput: 72.6 tps, Latency: 4842.77s
  44. Anthropic Claude Sonnet 5 — Throughput: 72.2 tps, Latency: 2365.22s
  45. OpenAI gpt-5.2-chat-latest — Throughput: 72.0 tps, Latency: 3630.38s
  46. Google Nano Banana 2 (Gemini 3.1 Flash Image 🍌) — Throughput: 71.7 tps, Latency: 16479.81s
  47. Anthropic Claude Opus 4.7 — Throughput: 68.1 tps, Latency: 2966.60s
  48. Anthropic Claude Opus 4.5 — Throughput: 67.7 tps, Latency: 3284.22s
  49. Stepfun step-3.5-flash — Throughput: 67.5 tps, Latency: 194.00s
  50. OpenAI GPT-5.4 Nano — Throughput: 67.5 tps, Latency: 12255.50s
  51. Anthropic Claude Fable 5 — Throughput: 67.3 tps, Latency: 5153.04s
  52. OpenAI GPT-5.5 — Throughput: 67.2 tps, Latency: 3173.92s
  53. OpenAI GPT-5.4 Mini — Throughput: 67.1 tps, Latency: 8377.00s
  54. Anthropic Claude Opus 4.8 — Throughput: 66.1 tps, Latency: 2699.80s
  55. xAI grok-4-fast-reasoning — Throughput: 65.9 tps, Latency: 6836.00s
  56. Google gemini-2.5-flash-lite — Throughput: 63.7 tps, Latency: 0.00s
  57. Xiaomi MiMo-V2.5 — Throughput: 60.7 tps, Latency: 4833.59s
  58. Anthropic Claude Sonnet 4.6 — Throughput: 60.3 tps, Latency: 2587.47s
  59. OpenAI GPT-5.1 Chat — Throughput: 54.3 tps, Latency: 1174.50s
  60. OpenAI GPT-5.2 — Throughput: 53.7 tps, Latency: 3459.88s
  61. Google Gemini 3.1 Flash-Lite Preview — Throughput: 53.4 tps, Latency: 369.00s
  62. OpenAI GPT-5.1 — Throughput: 51.4 tps, Latency: 1241.08s
  63. Anthropic Claude Sonnet 4.5 — Throughput: 51.3 tps, Latency: 2450.88s
  64. Moonshot moonshot-v1-8k — Throughput: 50.4 tps, Latency: 1680.12s
  65. Anthropic Claude Opus 4.6 — Throughput: 49.2 tps, Latency: 3510.84s
  66. DeepSeek deepseek-reasoner — Throughput: 47.3 tps, Latency: 314.84s
  67. Z.ai GLM 5.2 — Throughput: 46.0 tps, Latency: 837.50s
  68. DeepSeek DeepSeek-V3.2 — Throughput: 41.2 tps, Latency: 1136.00s
  69. OpenAI gpt-4.1 — Throughput: 40.3 tps, Latency: 2448.67s
  70. OpenAI gpt-5-mini — Throughput: 39.5 tps, Latency: 10089.19s
  71. OpenAI gpt-4.1-nano — Throughput: 38.4 tps, Latency: 1158.70s
  72. Anthropic Claude Opus 4.1 — Throughput: 38.0 tps, Latency: 2566.41s
  73. OpenAI o1 — Throughput: 37.3 tps, Latency: 0.00s
  74. OpenAI gpt-3.5-turbo-0125 — Throughput: 37.1 tps, Latency: 15273.50s
  75. DeepSeek DeepSeek-V4-Flash — Throughput: 33.2 tps, Latency: 1967.17s
  76. ByteDance Doubao-Seed-2.0-pro — Throughput: 33.0 tps, Latency: 0.00s
  77. Google Gemini 3 Pro Preview — Throughput: 32.6 tps, Latency: 0.00s
  78. MiniMax MiniMax-M2.7 — Throughput: 32.3 tps, Latency: 13818.20s
  79. OpenAI gpt-4o-mini — Throughput: 32.1 tps, Latency: 5427.30s
  80. OpenAI GPT-5.6 Sol — Throughput: 32.1 tps, Latency: 19184.99s
  81. Alibaba qwen-max — Throughput: 27.7 tps, Latency: 0.00s
  82. OpenAI GPT Image 2 — Throughput: 26.5 tps, Latency: 93902.40s
  83. OpenAI gpt-oss-120b — Throughput: 23.4 tps, Latency: 0.00s
  84. DeepSeek deepseek-v3 — Throughput: 22.5 tps, Latency: 0.00s
  85. MiniMax MiniMax M3 — Throughput: 22.1 tps, Latency: 0.00s
  86. OpenAI GPT Image 2 Develop — Throughput: 22.0 tps, Latency: 83237.63s
  87. Alibaba qwen3-vl-flash — Throughput: 21.7 tps, Latency: 0.00s
  88. Moonshot kimi-k2-0711-preview — Throughput: 21.5 tps, Latency: 1090.00s
  89. OpenAI gpt-4o — Throughput: 21.3 tps, Latency: 6536.20s
  90. OpenAI GPT-5.4 Pro — Throughput: 19.6 tps, Latency: 1184.12s
  91. MiniMax MiniMax M2.5 Lightning — Throughput: 18.5 tps, Latency: 795.00s
  92. Google Nano Banana Pro (Gemini 3 Pro Image 🍌) — Throughput: 18.5 tps, Latency: 27435.99s
  93. OpenAI o4-mini-deep-research — Throughput: 17.8 tps, Latency: 495.00s
  94. Moonshot kimi-k2-0905-preview — Throughput: 17.3 tps, Latency: 903.25s
  95. OpenAI gpt-3.5-turbo-16k — Throughput: 17.2 tps, Latency: 0.00s
  96. OpenAI gpt-3.5-turbo-1106 — Throughput: 17.2 tps, Latency: 594.00s
  97. DeepSeek DeepSeek-V4-Pro — Throughput: 17.0 tps, Latency: 5996.67s
  98. OpenAI gpt-4 — Throughput: 15.1 tps, Latency: 6322.00s
  99. OpenAI o3 — Throughput: 12.9 tps, Latency: 0.00s
  100. Moonshot kimi-k2-thinking-turbo — Throughput: 12.7 tps, Latency: 908.50s