GLOBAL FUNN • BUILD 33
Token Savings Benchmark
Measure actual usage before and after context compression. No guessed savings claims.
MEASURED RESULTS • ALL SAVED SAMPLES
Samples
0
Tokens saved
0
Token reduction
0.0%
Output bytes reduced
0.0%
Quality change
0.00 / 5
Totals are based only on the measurements you enter. Compare similar tasks, same model and comparable quality ratings. Lower token count alone is not a win if answer quality falls.
Record a benchmark
Benchmark history
No benchmark samples yet. Enter the same task's before/after measurements to start a reliable comparison.
Privacy: records are stored in this browser's localStorage only. No account data is fetched, no API key is requested, and no data is sent to GLOBAL FUNN servers. Clear browser storage only after exporting a backup.