Fastest AI Models 2025 — Speed Benchmarks

Tokens per second, time-to-first-token, and throughput for the major AI models. Speed matters for detection too — faster models write more uniformly, which affects detectability.

5 min read2025 Data

Speed in AI models is measured primarily in tokens per second (TPS) — how quickly the model generates output. This matters for user experience, but it also has an interesting implication for detection: faster, lower-cost models (designed for throughput) tend to use more formulaic patterns than slower, higher-quality models.

Speed Rankings — 2025

Model Speed (TPS) Quality Tier Detectability
Groq (Llama 3.1 70B) ~800 TPS Good High — formulaic output
Gemini 1.5 Flash ~250 TPS Good High — speed model patterns
GPT-4o mini ~160 TPS Good High — vocab markers present
Claude 3 Haiku ~150 TPS Good Medium-High
GPT-4o ~80 TPS Excellent High — vocab patterns strong
Claude 3.5 Sonnet ~70 TPS Excellent Medium — hedging style
Gemini 1.5 Pro ~60 TPS Excellent High — encyclopedic style
DeepSeek V3 ~55 TPS Excellent High — very formal output

TPS figures are approximate output token throughput via API. Varies significantly by load, region, and prompt type.

Speed vs. Detection: The Relationship

There's a consistent pattern: faster models trained for throughput produce more predictable output. More predictable output = more detectable. This makes intuitive sense — speed optimization often means reducing diversity in token selection.

Slower, higher-quality models like Claude 3.5 Sonnet and GPT-4o are harder to detect because they have more "temperature" in their outputs — more variance in word choice and sentence structure. They're still detectable (70–80%), but less so than flash/mini models (85–92%).

Which Model Produces the Most Detectable Text?

Based on our testing across all 12 detection signals:

  1. Groq (Llama 3.1) — fastest and most formulaic. Very high detection rate.
  2. GPT-4o / GPT-4o mini — strong vocabulary marker pattern. Consistent detection.
  3. Gemini 1.5 Flash/Pro — encyclopedic style is distinctive. Detects reliably.
  4. DeepSeek V3 — very formal academic register even on casual prompts.
  5. Claude 3.5 Sonnet — least detectable of the major models. Epistemic hedging style is distinct but scores lower on standard vocab signals.
🔍
Want to test detectability yourself? Use the free detector on outputs from different models and compare scores.