| Supplier, product, version |
nick-vas, Hyperdot, 0.1.0 |
| Model, plugin |
claude-haiku-5-5, loaded |
| Scale |
2026-10 (method) |
| Standard programme |
A-baseline, 8 tasks of benchmark/token-benchmark.json (sha256 f521ee805d02), 24 sessions |
| Tool efficiency class |
G |
| Agent Efficiency Index |
107.5 |
| Tokens per solved task |
113,548 |
| Answers that pass |
79.2% |
| Cost per solved task |
$0.0058 (Claude Code's figure) |
| Median session time |
13 s |
| Coverage class |
A (index 97.2: functions 93.5%, error codes 98.2%, commands 100%) |
| Runs |
20261023-091349 (2.1.309 (Claude Code)) |
| Note |
adversarial review: 62 findings, 59 fixed with regression tests |
