2nth.hw Reports

2026-05-15
Best Model
gemma4:e2b
23/23 passed, 44s avg
Arena Tests
99
97 passed across 5 models
Showcase
27
deliverables from 12 agents
Skills Audited
128
avg 5.0/10 completeness
Knowledge
18
domain articles

Model Arena 5 models

#ModelPass RateLatencyAvg Tokens
1gemma4:e2b100% (23/23)44s2118
2gemma4:e4b100% (19/19)80.4s2268
3qwen3:8b100% (19/19)88.2s2018
4deepseek-r1:8b95% (18/19)96.6s2173
5qwen3:14b95% (18/19)155.7s2055

Workload Runs 7 completed

WorkloadStatusTasksFailedDate
knowledgecompleted17/1602026-05-15 04:21:42
brief-decompcompleted14/6002026-05-15 01:39:45
skill-auditcompleted255/30002026-05-15 00:04:26
showcasecompleted26/5202026-05-14 22:52:18
arenacompleted1/202026-05-14 19:58:34
arenacompleted1/202026-05-14 19:49:17
arenacompleted95/20002026-05-14 19:43:14