The demo compared Jev and OpenAI's Decisions API by having both play the same three browser games with identical conditions. Jev won 83% of games overall, with both models achieving similar accuracy on the phishing game, though OpenAI refused some actions without explanation.

Name: The demo compared Jev and OpenAI's Decisions API by having both play the same three browser games with identical conditions. Jev won 83% of games overall, with both models achieving similar accuracy on the phishing game, though OpenAI refused some actions without explanation.
Uploaded: 2026-10-16T18:00:28.380Z
Channel: _briancoombs
Description: The demo compared Jev and OpenAI's Decisions API by having both play the same three browser games with identical conditions. Jev won 83% of games overall, with both models achieving similar accuracy on the phishing game, though OpenAI refused some actions without explanation.

_briancoombsevaluation-benchmarking13 views · 1 likes

Discovered 2026-10-16, refreshed 2026-10-16. Descriptions and stats are pulled from the project's own X post and refreshed automatically — they aren't independently verified by JevTracks beyond the initial eligibility check.