Skip to content

Actions: benchflow-ai/awesome-evals

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
128 workflow runs
128 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 whatbroke to 5f (observability + eval platforms) Awesome-Evals Responder #84: Pull request #51 opened by arthi-arumugam-git
12s
12s
Eval Scan (audit + update) Eval Scan (audit + update) #44: Scheduled
28s main
main
28s
Eval Scan (audit + update) Eval Scan (audit + update) #43: Scheduled
29s main
main
29s
Add greenproof to §8 (verifiers) Awesome-Evals Responder #83: Pull request #50 opened by zxyasfas
16s
16s
Eval Scan (audit + update) Eval Scan (audit + update) #42: Scheduled
32s main
main
32s
Eval Scan (audit + update) Eval Scan (audit + update) #41: Scheduled
2m 34s main
main
2m 34s
Add verdict4 to 5a (eval frameworks & harnesses) Awesome-Evals Responder #82: Pull request #49 opened by devongenerally-png
14s
14s
Eval Scan (audit + update) Eval Scan (audit + update) #40: Scheduled
2m 25s main
main
2m 25s
Eval Scan (audit + update) Eval Scan (audit + update) #39: Scheduled
1m 52s main
main
1m 52s
Eval Scan (audit + update) Eval Scan (audit + update) #38: Scheduled
2m 35s main
main
2m 35s
Add Tura coding-agent cost study Awesome-Evals Responder #81: Pull request #48 opened by Yohjisakamoto
16s
16s
Add: Human-AI productivity claims as time-to-acceptance (Section 6, measurement validity) Awesome-Evals Responder #80: Pull request #47 opened by ChaoYue0307
10s
10s
Eval Scan (audit + update) Eval Scan (audit + update) #37: Scheduled
2m 0s main
main
2m 0s
Eval Scan (audit + update) Eval Scan (audit + update) #36: Scheduled
1m 20s main
main
1m 20s
Add "Your LLM-as-Judge Is Lying to You" to §8 (LLM-as-judge & verifiers) Awesome-Evals Responder #79: Pull request #46 opened by loopandretry
15s
15s
Eval Scan (audit + update) Eval Scan (audit + update) #35: Scheduled
2m 4s main
main
2m 4s
§6: add pdfhell cross-modality study — PDF leaderboard nearly inverts on pixels Awesome-Evals Responder #78: Pull request #45 opened by siddharthsrivastava
11s
11s
§6: add eval-framework-benchmark — cross-framework disagreement study (κ ≈ 0.03) Awesome-Evals Responder #77: Pull request #44 opened by siddharthsrivastava
10s
10s
Eval Scan (audit + update) Eval Scan (audit + update) #34: Scheduled
2m 1s main
main
2m 1s
Add PerspectiveGap and Universal Magic Words Awesome-Evals Responder #76: Pull request #43 opened by WhymustIhaveaname
11s
11s
Eval Scan (audit + update) Eval Scan (audit + update) #33: Scheduled
1m 41s main
main
1m 41s
Eval Scan (audit + update) Eval Scan (audit + update) #32: Scheduled
2m 18s main
main
2m 18s
Add Doubleword benchmark-forecasting blog to §6 (Benchmark vs. eval) Awesome-Evals Responder #75: Issue comment #42 (comment) created by jaedmunt
1s
1s
Add Doubleword benchmark-forecasting blog to §6 (Benchmark vs. eval) Awesome-Evals Responder #74: Pull request #42 opened by jaedmunt
15s
15s
Add two benchmark-auditing resources: Berkeley's 'How We Broke Top AI Agent Benchmarks' (§10) + RewardHackingAgents (§6) Awesome-Evals Responder #73: Pull request #41 opened by dkx955
10s
10s