RAG or not — compare. learn. decide.
Live Benchmark
Run 7 real AWS-docs queries through four retrieval strategies and get empirical numbers on cost, latency, answer quality, and carbon — so you can decide whether RAG is worth it for your organisation.
Advanced: Benchmark on your own docs
Upload your own PDFs or TXTs and benchmark retrieval against them with up to 10 iterations. Requires an access key — request one below if you don't have one.
Request access to advanced benchmark
Leave your email and we'll send you an access key to run benchmarks on your own documents. Your email is used only to send the key — we don't share it or use it for anything else. See our Privacy Policy.
Mode Comparison (illustrative — run benchmark for live data)
Numbers below are representative of the demo corpus runs. Hit “Run Benchmark” above to replace these with your own live results.
RAG vs Flat baseline: adds $0.00041 per query in LLM cost — free retrieval modes cost nothing beyond Lambda compute.
| Mode | AccuracyFor live runs: avg_confidence × 100, where confidence is the retrieval model's score for how relevant the top chunks were (0–1). LLM-only has no retrieval step so it shows no confidence. Static numbers are illustrative from demo corpus runs. | LatencyEnd-to-end time measured in the browser with performance.now() around the full fetch() call — includes network round-trip, not just Lambda execution. | Cost / querydata.llm_stats.cost_usd from the Lambda — Bedrock token billing cost. Exactly $0.00000 for Flat and Hierarchical (no LLM call). For LLM-only and RAG, reflects input + output token pricing. | What it means for your org |
|---|---|---|---|---|
| Flat (Lexical) | 71% | 6ms | $0.00000 | Fast and free, but a single global ranking can surface off-topic chunks from unrelated docs. |
| Hierarchical | 79% | 11ms | $0.00000 | Narrowing to top documents first improves precision over Flat at a small extra compute cost. |
| LLM-only | 53% | 690ms | $0.00013 | No grounding — fluent, but frequently generic or wrong on service-specific details. |
| RAG | 91% | 860ms | $0.00041 | Retrieval grounds the answer before generation — highest accuracy, but the slowest and priciest mode. |
Impact Analytics
Illustrative — run the benchmark above to replace with live data. Grid intensity at 400 gCO₂/kWh. LLM/RAG energy derived from cost at ~2,615 Wh/$. All are order-of-magnitude estimates, not measurements.
| Mode | USD |
|---|---|
| Flat (Lexical) | $0.00000 |
| Hierarchical | $0.00000 |
| LLM-only | $0.00013 |
| RAG | $0.00041 |
| Mode | grams CO₂ |
|---|---|
| Flat (Lexical) | 0.0002g |
| Hierarchical | 0.0004g |
| LLM-only | 0.14g |
| RAG | 0.16g |
Flat and Hierarchical cost nothing beyond Lambda compute — no Bedrock call, no LLM billing.
RAG cost
$123.00/mo
$1496/yr
Flat / Hierarchical cost
~$0/mo
Lambda compute only
RAG CO₂ (est.)
49.20kg/mo
598.6kg/yr
Annual RAG CO₂ ≈ 3.0k km driven or 75k phone charges. Rough order-of-magnitude only (200 gCO₂/km, 8 gCO₂/charge).