Skip to content

Actions: Job-Bench/Job-Bench.github.io

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
29 workflow runs
29 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Add Qwen3.8-max Deploy site to GitHub Pages #28: Commit 38558b6 pushed by yichen-f
43s main
main
43s
Add Qwen3.8-max Deploy site to GitHub Pages #27: Commit cff4e05 pushed by yichen-f
47s main
main
47s
Add Meta's Muse Spark 1.2 at the top of the OpenCode leaderboard Deploy site to GitHub Pages #26: Commit 3040dbc pushed by 1GaryLi
48s main
main
48s
Correct the Kimi K3 score to 54.27 and backfill its breakdown Deploy site to GitHub Pages #25: Commit d1e98e3 pushed by 1GaryLi
47s main
main
47s
Backfill the per-occupation breakdown for GPT-5.6 SOL Deploy site to GitHub Pages #24: Commit 2d1e3cd pushed by 1GaryLi
46s main
main
46s
Add Kimi K3 and GPT-5.6 SOL to the OpenCode leaderboard Deploy site to GitHub Pages #23: Commit 37d8d91 pushed by 1GaryLi
45s main
main
45s
JobBench site Deploy site to GitHub Pages #22: Commit 110253e pushed by 1GaryLi
40s main
main
40s
JobBench site Deploy site to GitHub Pages #21: Commit 4ef7881 pushed by 1GaryLi
49s main
main
49s
JobBench site Deploy site to GitHub Pages #20: Commit 77c0622 pushed by 1GaryLi
1m 5s main
main
1m 5s
JobBench site Deploy site to GitHub Pages #19: Commit d763018 pushed by 1GaryLi
42s main
main
42s
JobBench site Deploy site to GitHub Pages #18: Commit a570604 pushed by 1GaryLi
50s main
main
50s
JobBench site Deploy site to GitHub Pages #17: Commit a87d118 pushed by 1GaryLi
43s main
main
43s
Note judge-model cost rationale in leaderboard footnote Deploy site to GitHub Pages #16: Commit f28bea1 pushed by 1GaryLi
52s main
main
52s
JobBench site Deploy site to GitHub Pages #15: Commit e70e33d pushed by 1GaryLi
47s main
main
47s
Remove Claude Opus 4.5 and Sonnet 4.5 from the OpenCode board Deploy site to GitHub Pages #14: Commit c6ebf92 pushed by 1GaryLi
15s main
main
15s
Update GPT-5.4/5.2 scores from Grok 4.3 re-judge; drop Gemini 3 Flash Deploy site to GitHub Pages #13: Commit 7ab6dbb pushed by 1GaryLi
43s main
main
43s
Update leaderboard to unified OpenCode runs with Grok 4.3 judge Deploy site to GitHub Pages #12: Commit b30ebb9 pushed by 1GaryLi
18s main
main
18s
Update workload ratios to 2.4x / 1.4x / 1.4x Deploy site to GitHub Pages #11: Commit 42c1bad pushed by 1GaryLi
47s main
main
47s
Align scores with NeurIPS 2026 paper Table 4 Deploy site to GitHub Pages #10: Commit 551cc36 pushed by 1GaryLi
1m 3s main
main
1m 3s
Update citation URL to job-bench-eval repo Deploy site to GitHub Pages #9: Commit 3b41b4d pushed by 1GaryLi
50s main
main
50s
Move citation block to bottom of page before footer Deploy site to GitHub Pages #8: Commit 647babe pushed by 1GaryLi
37s main
main
37s
Add BibTeX citation block to leaderboard section Deploy site to GitHub Pages #7: Commit 1eedee4 pushed by 1GaryLi
45s main
main
45s
Restore "Automation desire" label in TaskWorkflows Deploy site to GitHub Pages #6: Commit 7617224 pushed by 1GaryLi
40s main
main
40s
Replace "Human Desire" with "Human Will" across all user-facing copy Deploy site to GitHub Pages #5: Commit 4688b6f pushed by 1GaryLi
41s main
main
41s
Fix UChicago logo to clean wordmark style Deploy site to GitHub Pages #4: Commit 5a5af07 pushed by 1GaryLi
43s main
main
43s