Benchmarks
August 20, 2026 ยท View on GitHub
Generated by pnpm benchmark from committed deterministic fixtures. Token counts use the
project's provider-neutral V0.1 estimator and include the compression notice.
| Fixture | Original Tokens | Compressed | Reduction | Critical Evidence |
|---|---|---|---|---|
| Maven failure | 22,998 | 1,736 | 92.5% | PASS |
| Gradle failure | 60,943 | 123 | 99.8% | PASS |
| npm build | 44,527 | 3,028 | 93.2% | PASS |
| pytest | 42,732 | 2,669 | 93.8% | PASS |
| JSON API | 159,459 | 352 | 99.8% | PASS |
| HTML page | 57,321 | 145 | 99.7% | PASS |
| Generic log | 85,027 | 106 | 99.9% | PASS |
Critical Evidence is an exact-string gate over known errors, failing test names, exit information, or incident facts planted in each fixture. These numbers are not provider billing-token claims; provider tokenization varies.