Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
GPT-5.4 nano
61
Hy3 Preview
62
Pick Hy3 Preview if you want the stronger benchmark profile. GPT-5.4 nano only becomes the better choice if knowledge is the priority or you need the larger 400K context window.
Agentic
+11.5 difference
Knowledge
+6.5 difference
GPT-5.4 nano
Hy3 Preview
$0.2 / $1.25
$0 / $0
191 t/s
N/A
3.64s
N/A
400K
256K
Pick Hy3 Preview if you want the stronger benchmark profile. GPT-5.4 nano only becomes the better choice if knowledge is the priority or you need the larger 400K context window.
Hy3 Preview finishes one point ahead on BenchLM's provisional leaderboard, 62 to 61. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Hy3 Preview's sharpest advantage is in agentic, where it averages 54.4 against 42.9. The single biggest benchmark swing on the page is HLE, 37.7% to 25.5%. GPT-5.4 nano does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 nano is also the more expensive model on tokens at $0.20 input / $1.25 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Hy3 Preview. That is roughly Infinityx on output cost alone. GPT-5.4 nano gives you the larger context window at 400K, compared with 256K for Hy3 Preview.
Hy3 Preview is ahead on BenchLM's provisional leaderboard, 62 to 61. The biggest single separator in this matchup is HLE, where the scores are 37.7% and 25.5%.
GPT-5.4 nano has the edge for knowledge tasks in this comparison, averaging 53.2 versus 46.7. Inside this category, HLE is the benchmark that creates the most daylight between them.
Hy3 Preview has the edge for agentic tasks in this comparison, averaging 54.4 versus 42.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.