-
Notifications
You must be signed in to change notification settings - Fork 60
Pull requests: benchflow-ai/awesome-evals
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add "Your LLM-as-Judge Is Lying to You" to §8 (LLM-as-judge & verifiers)
#46
opened Jul 14, 2026 by
loopandretry
Loading…
§6: add pdfhell cross-modality study — PDF leaderboard nearly inverts on pixels
#45
opened Jul 12, 2026 by
siddharthsrivastava
Loading…
§6: add eval-framework-benchmark — cross-framework disagreement study (κ ≈ 0.03)
#44
opened Jul 12, 2026 by
siddharthsrivastava
Loading…
Add Doubleword benchmark-forecasting blog to §6 (Benchmark vs. eval)
#42
opened Jul 10, 2026 by
jaedmunt
Loading…
Add two benchmark-auditing resources: Berkeley's 'How We Broke Top AI Agent Benchmarks' (§10) + RewardHackingAgents (§6)
#41
opened Jul 9, 2026 by
dkx955
Loading…
Add TAC (Travel Agent Compassion) agentic benchmark to section 9
#39
opened Jul 9, 2026 by
darkness8i8
Loading…
Add Helium benchmarks (finance chain + cue-swap worldview)
#37
opened Jul 2, 2026 by
connerlambden
Loading…
Add Caliper (pass@k reliability harness for agent skills) to 5a
#34
opened Jul 1, 2026 by
edonadei
Loading…
ProTip!
Mix and match filters to narrow down what you’re looking for.