Back to explore

Jev vs GPT-5.4 dalam fact-check sulit: tidak ada perbedaan signifikan, biaya 1/50

Uji ulang komunitas menunjukkan Jev dan GPT-5.4 secara statistik tidak dapat dibedakan (selisih 3,3 poin), dengan biaya Jev sekitar seperlimapuluh.

I said Jev beat GPT-5.4 on hard fact-checks by 11.1 points. That was one run. Rerun five times, I can't tell them apart: 3.3 points, not significant. Jev costs a fiftieth as much. Raw runs: https://github.com/TheWayWithin/jev-bench… https://jamiewatters.work/journey/jev-ties-gpt-5-4…

Jev vs GPT-5.4 dalam fact-check sulit: tidak ada perbedaan signifikan, biaya 1/50 1
· 0 likesOpen on X