AI Model Speed Rankings
Models ranked by measured output throughput (tokens per second) and average latency.
- Google Gemini 3.1 Pro Preview — Throughput: 166.3 tps, Latency: 9327.33s
- Google Gemini 3.8 Flash — Throughput: 147.0 tps, Latency: 4527.38s
- Google Gemini 4 Hydrogen — Throughput: 90.6 tps, Latency: 0.00s
- Google Gemini 4 Neon — Throughput: 78.3 tps, Latency: 4779.00s
- Google Gemini 4 Carbon — Throughput: 3.8 tps, Latency: 0.00s
- Google Gemini 4 Argon — Throughput: 2.7 tps, Latency: 0.00s