Themed ranking
Lowest latency
Ranked by real measured median (p50) response latency at each model's best-performing provider, tracked daily. Lower is faster to first meaningful output.
As of November 7, 2026, Z.ai: GLM 5.3 (batch) ranks #1 for lowest latency at latency p50 140ms.
- #1 Z.ai: GLM 5.3 (batch) - Latency p50 140ms
- #2 OpenAI: gpt-oss-120b (batch) - Latency p50 154ms
- #3 NVIDIA: Nemotron 3.5 Lightning (free) - Latency p50 197ms
- #4 DeepSeek: DeepSeek V4.1 Flash (batch) - Latency p50 208ms
- #5 Mistral: Mistral Nemo - Latency p50 209ms
- #6 Google: Gemma 4 31B (free) - Latency p50 244ms
- #7 DeepSeek: DeepSeek V4 Flash 0423 - Latency p50 265ms
- #8 MiniMax: MiniMax M2.7 - Latency p50 267ms
- #9 Poolside: Laguna XS 2.1 (free) - Latency p50 268ms
- #10 NVIDIA: Nemotron 3 Ultra (free) - Latency p50 273ms
Source: OpenRouter (openrouter.ai/rankings), as of November 7, 2026.
Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Methodology: www.smophy.ai/benchmark/methodology
Token counts originate from each provider's own tokenizer and are not directly comparable across providers.