Helium Trades
HeliumTrades
AI & ML interests
None yet
Recent Activity
new activity 11 days ago
BGPT-OFFICIAL/refute:Preregistered score prediction: next frontier model on REFUTE new activity 11 days ago
OpenEvals/README:New Benchmark Dataset updated a dataset 11 days ago
HeliumTrades/helium-news-bias-corpusOrganizations
None yet
Preregistered score prediction: next frontier model on REFUTE
#12 opened 11 days ago
by HeliumTrades
New Benchmark Dataset
🚀 5
19
#2 opened 6 months ago
by 
burtenshaw
Live demo: Beat-48 Challenge Space
#8 opened 15 days ago
by HeliumTrades
Live demo: Beat-48 Challenge Space
#8 opened 15 days ago
by HeliumTrades
Replication kit: beat-48 + pair scorer + Colab
#7 opened 15 days ago
by HeliumTrades
Replication kit: beat-48 + pair scorer + Colab
#7 opened 15 days ago
by HeliumTrades
Quick-start: cue-swap flip-rate replication
#6 opened 15 days ago
by HeliumTrades
Quick-start: replicate scores with LiteLLM (5 prompts)
#6 opened 15 days ago
by HeliumTrades
Replication bounty + cue-swap scoring questions
#5 opened 15 days ago
by HeliumTrades
Replication bounty: first external run gets a landing-page credit
#4 opened 15 days ago
by HeliumTrades
Cue-swap examples that split models hardest
#4 opened 15 days ago
by HeliumTrades
Reproducing scores with LiteLLM / local models
#3 opened 15 days ago
by HeliumTrades
How we score cue-swap consistency
#3 opened 15 days ago
by HeliumTrades
Benchmark landing page with model charts
#2 opened 15 days ago
by HeliumTrades
Landing page and pair benchmark link
#2 opened 15 days ago
by HeliumTrades
Landing page with charts and rerun guide
#1 opened 15 days ago
by HeliumTrades