Topic
Agentic Workflow Performance Benchmarks
14 posts on agentic workflow performance benchmarks — part of benchmarks & performance on the n4n AI blog.
Why retries and self-correction slow down AI agents
Retries and self-correction loops inflate agent latency and cost without fixing root causes. We analyze where time goes and how to cut the tax.
Why agentic workflows amplify per-token latency costs
Agentic workflow latency amplification multiplies per-token delays across sequential steps. We break down the cause and show concrete mitigation tactics.
Multi-agent workflow latency vs single-agent baselines
Head-to-head comparison of multi-agent vs single-agent latency across capability, cost, throughput, and ergonomics, with a use-case verdict.
Measuring planning overhead in autonomous agent loops
A practical analysis of agent planning overhead latency in autonomous loops: how to measure it separately from tool use and why it dominates agent speed.
Measuring end-to-end latency in autonomous coding agents
A practical methodology to measure end-to-end coding agent latency for autonomous software agents, with instrumentation steps and runnable code.
How model choice affects agent task completion time
Model choice drives agent task completion time more than prompts or infra. We break down latency tradeoffs across model tiers with concrete agent loop examples.
How many seconds does a 5-step agent loop actually take?
Agent loop latency 5 steps: how sequential LLM calls, tool overhead, and caching shape whether your loop finishes in 15 or 60 seconds.
Agent loop latency: how context growth slows each step
Analyzes how agent loop context growth latency compounds each step, breaking latency assumptions, with concrete code and mitigation strategies for engineers.
Agent latency benchmark for long-horizon research tasks
A proper long-horizon agent latency benchmark measures end-to-end task time under failure, not token speed. We break down design, code, and tradeoffs.
Benchmarking coding agent latency on real GitHub issues
A practical analysis of coding agent latency benchmarks on real GitHub issues, showing where time goes and how to measure end-to-end wall-clock accurately.
Benchmarking browser-use agent latency across models
A practical browser-use agent latency benchmark comparing GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, and Llama 3.1 70B on speed, cost, and reliability for engineers.
AI agent latency benchmark: single-step vs multi-step tasks
A head-to-head comparison of agent latency single-step vs multi-step tasks across capabilities, cost, latency, ergonomics, and limits for engineers.
Agent latency benchmark: ReAct vs plan-and-execute
Benchmarking ReAct vs plan-and-execute latency: head-to-head comparison of cost, throughput, ergonomics, and limits with code examples and a use-case verdict.
Agent latency benchmark: Claude Opus 4.5 vs GPT-4.1
Head-to-head benchmark of Claude Opus 4.5 vs GPT-4.1 agent latency across capabilities, cost, throughput, and ergonomics for production AI agents.
More topics in benchmarks & performance
- Benchmark Methodology and Measurement14
- Code Generation Latency for Dev Tools14
- Flagship Model Speed Showdown14
- Llama 4 Inference Speed by Provider14
- Price-Performance Rankings14
- Provider Uptime and Reliability Benchmarks14
- Reasoning Model Latency Overhead14
- Customer Support Chatbot Latency13
- DeepSeek Performance Benchmarks13
- GPU Inference Benchmarks13
- Long-Context Latency Benchmarks13
- Model Size vs Inference Speed Tradeoffs13