Local LLM N-vs-N benchmark harness — llama.cpp via llama-swap, quality/latency/cost scoring.
active 2026-04-18 → 2026-08-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 123 days from 2026-04-18 to 2026-08-18. Pushes: 22 total, peak 4 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 9 total, peak 3 in a day. Comments: 24 total, peak 4 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| AlbinoGeek | 40 | 21 | 0 | 12 |
| gissf1 | 11 | 0 | 0 | 9 |
| Copilot | 3 | 0 | 0 | 3 |
| dependabot[bot] | 3 | 1 | 2 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#41dependabot[bot]2026-06-13 12:42
- Issue comment#33gissf12026-06-06 04:54Schema PR: agent_traces, uplift_baseline_task_id, cyber_safety category (blocks C4 + C6 from #30)
- Issue#36AlbinoGeek2026-06-05 01:46Basic results reporting: bakeoff-report CLI reads from BAKEOFF_DATA_DIR (Phase 1)
- Issue#30AlbinoGeek2026-06-04 23:08Cyber capability proxy test design — bakeoff integration plan
- Issue comment#13AlbinoGeek2026-05-29 04:26Design and implement test run scheduling queue
- Issue comment#22gissf12026-05-27 11:46Hardware tables disk persistence — analysis and layout
- Issue comment#22gissf12026-05-27 01:19Hardware tables disk persistence — analysis and layout
- Issue comment#22AlbinoGeek2026-05-25 10:46Hardware tables disk persistence — analysis and layout
- Issue comment#15AlbinoGeek2026-05-23 05:40bakeoff: model descriptor file format and capability ingestion
- Issue comment#15gissf12026-05-23 05:12bakeoff: model descriptor file format and capability ingestion
- Issue comment#13gissf12026-05-22 20:37Design and implement test run scheduling queue
- Issue#15AlbinoGeek2026-05-22 14:25bakeoff: model descriptor file format and capability ingestion
- Issue comment#13AlbinoGeek2026-05-22 00:14Design and implement test run scheduling queue
- Issue comment#13gissf12026-05-22 00:08Design and implement test run scheduling queue
- Issue comment#14AlbinoGeek2026-05-21 08:26Isn't ollama equally trustworthy?
- Issue comment#14gissf12026-05-20 23:25Isn't ollama equally trustworthy?
- Issue comment#8AlbinoGeek2026-05-20 06:38Additional Performance Metrics
- Issue comment#8gissf12026-05-17 06:39Additional Performance Metrics
- Issue comment#8AlbinoGeek2026-05-16 06:27Additional Performance Metrics
- Issue#11AlbinoGeek2026-05-16 06:25queue: document and seed P0/P1/P2 model testing queue
- Issue#10AlbinoGeek2026-05-16 06:18metrics: add TFLOPS utilization and optional CPU timing fields
- Issue#10AlbinoGeek2026-05-16 06:09metrics: add TFLOPS utilization and optional CPU timing fields
- Issue comment#7gissf12026-05-14 00:44models to test
- Pull request#6dependabot[bot]2026-05-02 19:23
- Issue comment#5AlbinoGeek2026-04-27 01:44campaign: establish bakeoff results publication plane
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.