Open-source library for scalable, reproducible evaluation of AI models and benchmarks.
Python · active 2025-09-19 → 2026-07-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 314 days from 2025-09-19 to 2026-07-29. Pushes: 1,575 total, peak 34 in a day. Pull requests: 603 total, peak 17 in a day. Issues: 35 total, peak 3 in a day. Comments: 751 total, peak 35 in a day. Stars: 91 total, peak 7 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 |
|---|---|---|---|---|
| copy-pr-bot[bot] | 638 | 449 | 0 | 189 |
| marta-sd | 404 | 163 | 27 | 125 |
| nemo-automation-bot[bot] | 276 | 103 | 173 | 0 |
| agronskiy | 250 | 107 | 30 | 45 |
| AWarno | 216 | 138 | 19 | 40 |
| github-actions[bot] | 214 | 0 | 210 | 0 |
| wprazuch | 188 | 124 | 20 | 35 |
| athitten | 176 | 31 | 14 | 67 |
| ko3n1g | 109 | 82 | 14 | 9 |
| pribalta | 93 | 4 | 1 | 75 |
| prokotg | 68 | 24 | 5 | 22 |
| pablo-garay | 67 | 31 | 14 | 14 |
| lbliii | 63 | 49 | 8 | 4 |
| Glorf | 63 | 28 | 8 | 15 |
| gchlebus | 62 | 30 | 9 | 18 |
| piojanu | 51 | 39 | 8 | 2 |
| AdamRajfer | 48 | 33 | 5 | 7 |
| chtruong814 | 46 | 24 | 9 | 7 |
| ka00ri | 42 | 26 | 7 | 3 |
| jgerh | 40 | 0 | 0 | 31 |
Recent activity
Latest issues, pull requests and releases
- Pull request#1058ritaneves2026-06-04 12:23
- Pull request#1042marta-sd2026-06-01 11:37
- Pull request#1034github-actions[bot]2026-05-27 01:45
- Issue comment#1029copy-pr-bot[bot]2026-05-25 09:04fix: remove unused doc file containing broken links
- Pull request#1025nemo-automation-bot[bot]2026-05-22 14:54
- Issue comment#1024ko3n1g2026-05-22 13:12ci: pin FW-CI-templates to NVIDIA-NeMo/FW-CI-templates#480 (mirror branch protection)
- Issue comment#1006wprazuch2026-05-12 10:33chore: align version to 0.3.0 (drop internal 0.13.0 counter)
- Issue comment#1000wprazuch2026-05-11 10:37feat(solvers): OracleSolver + Terminal-Bench-Hard for infra-ceiling measurement
- Pull request#985github-actions[bot]2026-05-06 22:33
- Pull request#985github-actions[bot]2026-05-06 22:33
- Issue comment#982copy-pr-bot[bot]2026-05-06 16:50feat: add ATIF retrieved context metric
- Pull request#979nemo-automation-bot[bot]2026-05-06 15:48
- Issue#974github-actions[bot]2026-05-06 04:19lm-evaluation-harness container: shared aiohttp ClientSession with ClientTimeout(total=...) aborts long benchmark runs (e.g. MMLU-Pro 12k prompts)
- Issue comment#971copy-pr-bot[bot]2026-05-05 17:31beep boop 🤖: Bumping NeMo Evaluator to v0.2.9
- Pull request#971github-actions[bot]2026-05-05 17:31
- Issue comment#963copy-pr-bot[bot]2026-05-05 09:01beep boop 🤖: Bumping NeMo Evaluator to v0.2.9
- Issue comment#959copy-pr-bot[bot]2026-05-04 11:53chore(ci): port cicd-main.yml + install-test.yml from main (trimmed)
- Issue comment#958coderabbitai[bot]2026-05-04 11:29chore(ci): port Group A workflows from main (verbatim)
- Issue comment#956copy-pr-bot[bot]2026-05-04 10:19chore(ci): plug OSS PR checks + align pre-commit/Makefile
- Pull request#950SandyChapman2026-04-29 16:12
- Issue comment#947chtruong8142026-04-29 01:23ci: Remove Azure in Github CI
- Issue comment#947chtruong8142026-04-29 01:01ci: Remove Azure in Github CI
- Pull request#947github-actions[bot]2026-04-29 01:01
- Issue#579github-actions[bot]2026-04-23 23:04flash-attn build issue (method: pip install): ModuleNotFoundError: No module named 'torch'
- Issue#605pruprakash2026-04-21 03:16Can I use Nemo evaluator without launcher?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 91 stars here means stars gained during the window, not the repo's star count.