BMS

Start typing to search the publication.

Shareable benchmark table

PoolTogether pilot metrics

Detection, quality, runtime, token, and cost observations from one run per model.

Table 01 · Pilot results

PoolTogether pilot metrics

PublishedCase study1 run/modelManual GT
Detection, quality, runtime, token, and cost observations from one run per model.
MetricGPT-5.6 SolGrok 4.6 Build
Detection score100%0.1%
Recall100%50%
Precision66.7%25%
Wall time8m 26s26m 7s
Processed tokens813k3.95m
Estimated cost$1.32$3.24
Table 01Detection, quality, runtime, token, and cost observations from one run per model.

Harnesses differed. Ground truth was manually reconstructed; cost bases are not invoice-equivalent.

BMSbms.kyokasuigetsu.xyz
Download CSVDownload PNGShare table
Static image: https://bms.kyokasuigetsu.xyz/tables/pilot-metrics.png

Read the source publication