Skip to content

Actions: vercel/next-evals-oss

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
76 workflow runs
76 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
Re-run tier-1 models on agent-043 after its grader fix (#115) eval cache check #78: Commit 7503613 pushed by gaojude
46s main
main
46s
Re-run tier-1 models on agent-043 after its grader fix eval cache check #77: Pull request #115 opened by gaojude
46s evals-043-results
evals-043-results
46s
feat(experiments): add cursor-grok-4.6-xhigh eval cache check #76: Pull request #114 opened by bompus
Action required bompus:feat/cursor-grok-4.6-xhigh
bompus:feat/cursor-grok-4.6-xhigh
Action required
Rerun active models on latest canary; retire Composer 1.5; refresh pr… eval cache check #75: Commit e681713 pushed by gaojude
40s main
main
40s
Rerun active models on latest canary; retire Composer 1.5; refresh prices eval cache check #74: Pull request #113 synchronize by gaojude
38s rerun-active-models-0826
rerun-active-models-0826
38s
Rerun active models on latest canary; retire Composer 1.5; refresh prices eval cache check #73: Pull request #113 synchronize by gaojude
35s rerun-active-models-0826
rerun-active-models-0826
35s
Bump @vercel/agent-eval from ^1.5.1 to ^2.2.1 (#112) eval cache check #72: Commit 21d1095 pushed by gaojude
1m 25s main
main
1m 25s
Bump @vercel/agent-eval to ^2.2.1 eval cache check #71: Pull request #112 opened by gaojude
58s bump/agent-eval-2.2.1
bump/agent-eval-2.2.1
58s
Make a fresh clone runnable: bootstrap, preflight, and honest setup d… eval cache check #70: Commit ed191f7 pushed by gaojude
59s main
main
59s
Make the eval setup reproducible from a fresh clone eval cache check #69: Pull request #111 opened by gaojude
1m 1s jude/next-evals-oss-sandbox
jude/next-evals-oss-sandbox
1m 1s
Make a fresh clone runnable: bootstrap, preflight, and honest setup docs eval cache check #68: Pull request #110 opened by gaojude
57s next-evals-oss-sandbox
next-evals-oss-sandbox
57s
Bump @vercel/agent-eval to 1.5.1 (#109) eval cache check #67: Commit b162ce1 pushed by gaojude
1m 0s main
main
1m 0s
Bump @vercel/agent-eval to 1.5.1 (credential redaction) eval cache check #66: Pull request #109 opened by gaojude
58s jude/bump-agent-eval-1.5.1
jude/bump-agent-eval-1.5.1
58s
Scrub leaked AI Gateway credentials from committed transcripts (#108) eval cache check #65: Commit 48019d9 pushed by gaojude
57s main
main
57s
Scrub leaked AI Gateway credentials from committed transcripts eval cache check #64: Pull request #108 synchronize by gaojude
1m 1s jude/scrub-leaked-oidc-tokens
jude/scrub-leaked-oidc-tokens
1m 1s
Scrub leaked AI Gateway credentials from committed transcripts eval cache check #63: Pull request #108 opened by gaojude
54s jude/scrub-leaked-oidc-tokens
jude/scrub-leaked-oidc-tokens
54s
Add Grok 4.6 eval results (22/24 base, 22/24 with AGENTS.md) (#107) eval cache check #62: Commit 88ec653 pushed by gaojude
55s main
main
55s
Add Grok 4.6 eval results (22/24 base, 22/24 with AGENTS.md) eval cache check #61: Pull request #107 opened by gaojude
52s jude/grok-4.6-evals
jude/grok-4.6-evals
52s
Add Claude Opus 5 and Claude Sonnet 5 eval results (#106) eval cache check #60: Commit 4d1fd49 pushed by gaojude
57s main
main
57s
Add Claude Opus 5 and Claude Sonnet 5 eval results eval cache check #59: Pull request #106 synchronize by gaojude
55s jude/add-opus-5-sonnet-5-deepseek-v4-pro-evals
jude/add-opus-5-sonnet-5-deepseek-v4-pro-evals
55s
Add Claude Opus 5 and Claude Sonnet 5 eval results eval cache check #58: Pull request #106 opened by gaojude
1m 4s jude/add-opus-5-sonnet-5-deepseek-v4-pro-evals
jude/add-opus-5-sonnet-5-deepseek-v4-pro-evals
1m 4s
Export per-eval list cost for nextjs.org/evals (#102) eval cache check #56: Commit eb81964 pushed by gaojude
48s main
main
48s
Export per-eval list cost for nextjs.org/evals eval cache check #55: Pull request #102 synchronize by gaojude
48s jude/rerun-gpt54-agent030
jude/rerun-gpt54-agent030
48s
Port the eval suite to Harbor task format eval cache check #54: Pull request #103 synchronize by gaojude
50s jude/harbor-port
jude/harbor-port
50s
Export per-eval list cost for nextjs.org/evals eval cache check #53: Pull request #102 synchronize by gaojude
49s jude/rerun-gpt54-agent030
jude/rerun-gpt54-agent030
49s