Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Hy3 Preview
60
MAI-Thinking-1
65
Verified leaderboard positions: Hy3 Preview unranked · MAI-Thinking-1 #23
Pick MAI-Thinking-1 if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if agentic is the priority.
Agentic
+8.4 difference
Coding
+11.0 difference
Knowledge
+23.2 difference
Inst. Following
+21.9 difference
Hy3 Preview
MAI-Thinking-1
$0 / $0
N/A
N/A
N/A
N/A
N/A
256K
256K
Pick MAI-Thinking-1 if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if agentic is the priority.
MAI-Thinking-1 is clearly ahead on the provisional aggregate, 65 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MAI-Thinking-1's sharpest advantage is in knowledge, where it averages 69.9 against 46.7. The single biggest benchmark swing on the page is IFBench, 63.1% to 85%. Hy3 Preview does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
MAI-Thinking-1 is ahead on BenchLM's provisional leaderboard, 65 to 60. The biggest single separator in this matchup is IFBench, where the scores are 63.1% and 85%.
MAI-Thinking-1 has the edge for knowledge tasks in this comparison, averaging 69.9 versus 46.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
MAI-Thinking-1 has the edge for coding in this comparison, averaging 71 versus 60. Inside this category, Terminal-Bench 2.0 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 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
MAI-Thinking-1 has the edge for instruction following in this comparison, averaging 85 versus 63.1. Inside this category, IFBench 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.