benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
voices
@RyanLopopolo on AI benchmarks
3 quotes from AI researchers about benchmarks, models, and evaluation
"It's the first one that's merged top tier coding. So it's codeex level coding and reasoning. General reasoning both in one model."
Ryan Lopopolo
@@RyanLopopolo
·
2026-04-07
view on x
GPT-5.4
"That's another big thing with 5.4, million token content which is huge in agentic. You can just run for longer before you have to compact."
Ryan Lopopolo
@@RyanLopopolo
·
2026-04-07
view on x
GPT-5.4
"To have 53 and then spark and 54 come out within like what feels like a month is just a phenomenally fast. This exactly a month ago it's 53 and yesterday was 54."
Ryan Lopopolo
@@RyanLopopolo
·
2026-04-07
view on x
GPT-5.4