AI Model Speed Rankings
Models ranked by measured output throughput (tokens per second) and average latency.
- Google gemini-2.5-flash — Throughput: 103.9 tps, Latency: 0.00s
- Google Gemini 4 Hydrogen — Throughput: 81.2 tps, Latency: 6932.00s
- Google Gemini 4 Argon — Throughput: 67.2 tps, Latency: 7971.50s
- Google Gemini 3.7 Flash — Throughput: 56.3 tps, Latency: 0.00s
- Google Gemini 4 Carbon — Throughput: 54.3 tps, Latency: 18663.53s
- Google Gemini 3.8 Flash — Throughput: 41.0 tps, Latency: 0.00s
- Google Nano Banana 2 (Gemini 3.1 Flash Image 🍌) — Throughput: 11.4 tps, Latency: 0.00s