Fetching metadata from the HF Docker repository...
Oct 6 16 days ago 15:52 Merge pull request #32 from DanielBlei/feat/sre-itbench-aa Running Taylor Agarwal
Feat/sre-itbench-aa Oct 5 17 days ago 15:50 feat: benchmark whitelist for rankings Daniel Blei
Oct 1 21 days ago 19:37 feat: add SRE category with ITBench AA results Daniel Blei
- Add SRE tab to the leaderboard with benchmark section rendering
- Catalog ITBench AA as an SRE benchmark (offline, incident-response)
- Add ITBench AA results for GLM 5.3, Qwen3.8 Flash Next, and Sonnet 5
- Add ITBench AA results for Opus 5.5 and Haiku 4.5 (Claude Code)
- Regenerate results.csv to include new runs
- Ignore local egg-info build artifacts
- Bump version to 0.2.0 Sep 3 19:41 Bump version to 0.1.1 19:38 Merge pull request #31 from redhat-et/feat/new-hf-space Taylor Agarwal
✨ Change target space to new ET space 13:42 ✨ Change target space to new ET space Sep 1 17:07 Merge pull request #29 from hemajv/add-shellbench-glm Taylor Agarwal
Add Shellbench GLM-5.2 results Aug 31 18:25 Add Shellbench GLM-5.2 results hemajv
Aug 21 14:00 Merge pull request #28 from redhat-et/feat/versioning Cédric P. Legendre
✨ Add project versioning 13:18 ✨ Add project versioning Aug 20 20:17 Merge pull request #27 from cplegendre/feature/configuration-lab Taylor Agarwal
Add configuration lab foundations and ranking refinements 20:11 Reduce ranking row height CP Legendre
19:52 Strengthen pairwise ranking regression assertions CP Legendre
19:45 Merge main and address ranking review feedback CP Legendre
14:38 Rename rankings tab to Pairwise Rankings Aug 19 19:09 Scale dense charts with result count CP Legendre
15:50 Rename metric-aware ranking order controls CP Legendre
15:28 Refine paired comparisons and ranking order CP Legendre
15:28 Add configuration metadata and comparison foundations CP Legendre
14:52 Force dark mode even when light mode is explicitly requested 14:41 Add efficiency, coding, generalist, and benchmark matrix views (#25) Cédric P. Legendre +1: rounakbende * Add analytics views and benchmark matrices
* Add Bradley-Terry rankings tab with filters for benchmarks, models, harnesses, and rank-by metric
* Address CR: fix eqvdata population, empty filter handling, and per-table error isolation
* Address leaderboard review feedback
* Round trade-off table values to one decimal
* Round trade-off table values to one decimal
* Round trade-off metrics to two decimals
* Round trade-off metrics to two decimals
---------
Co-authored-by: rounakbende10 <rounakbende@gmail.com> Aug 18 20:49 Revert "Add Bradley-Terry rankings tab (#26)" This reverts commit e08b34a37838e80b978b0620ee54c7e0d7f86463. 20:38 Add Bradley-Terry rankings tab (#26) Rounak Bende
* Add Bradley-Terry rankings tab with filters for benchmarks, models, harnesses, and rank-by metric
* Address CR: fix eqvdata population, empty filter handling, and per-table error isolation 16:33 Auto-update results.csv github-actions[bot]
16:32 Fix GPT-OSS-120B model name casing in shellbench result Aug 12 19:20 Merge pull request #24 from cplegendre/feature/token-efficiency Taylor Agarwal
Add token efficiency analysis and Pareto visualizations Aug 7 16:25 Finalize efficiency review updates CP Legendre
Aug 6 21:30 Add token efficiency analysis and visualizations CP Legendre
20:29 Merge pull request #23 from redhat-et/fix/legend-placement Taylor Agarwal
Fix legend overlap and improve leaderboard chart readability 15:16 Fix legend overlap and improve leaderboard chart readability taagarwa +1: Claude Move legend above charts with container-anchored positioning, make
charts horizontally scrollable with a per-bar minimum width, and
auto-scale the y-axis to fit data instead of a fixed 0-105 range.
Co-Authored-By: Claude <noreply@anthropic.com> 15:12 Auto-update results.csv github-actions[bot]
15:12 Fix GPT-OSS ansible benchmark name to match leaderboard grouping 12:50 Auto-update results.csv github-actions[bot]
12:49 Merge pull request #22 from redhat-et/fix/result-names Taylor Agarwal
Normalize result filenames to <benchmark>-<model>-<harness> order 12:48 Normalize result filenames to <benchmark>-<model>-<harness> order taagarwa +1: Claude Co-Authored-By: Claude <noreply@anthropic.com> 12:38 Auto-update results.csv github-actions[bot]
12:38 🐛 Fix typos in shellbench runs 12:30 Merge pull request #21 from hemajv/add-shellbench-results Taylor Agarwal
Add Shellbench results 02:27 Auto-update results.csv github-actions[bot]
02:26 Add GPT-OSS-120B results for all 3 benchmarks Aug 5 21:56 Add Shellbench results hemajv
Aug 2 23:56 Auto-update results.csv github-actions[bot]
23:55 Add Qwen3.6-27B-FP8 results for all 3 benchmarks 9 result files across SWE-bench Verified, SWE-bench Pro Ansible,
and RH SWE-bench with Claude Code, OpenCode, and Pi harnesses. Jul 29 16:45 Auto-update results.csv github-actions[bot]
16:45 Add Nemotron-120B Claude Code results for all 3 benchmarks Jul 27 19:03 Auto-update results.csv github-actions[bot]
19:03 Standardize harness URLs for OpenCode and Pi 18:52 Auto-update results.csv github-actions[bot]
18:51 Fix Mistral Pro Ansible benchmark repo/url inconsistencies 18:48 Auto-update results.csv github-actions[bot]
Cédric P. Legendre +1: rounakbende Unverified signature* Add analytics views and benchmark matrices * Add Bradley-Terry rankings tab with filters for benchmarks, models, harnesses, and rank-by metric * Address CR: fix eqvdata population, empty filter handling, and per-table error isolation * Address leaderboard review feedback * Round trade-off table values to one decimal * Round trade-off table values to one decimal * Round trade-off metrics to two decimals * Round trade-off metrics to two decimals --------- Co-authored-by: rounakbende10 <rounakbende@gmail.com>7ddc8cb