Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Opus 4.5
77
Hy3 Preview
62
Verified leaderboard positions: Claude Opus 4.5 #9 · Hy3 Preview unranked
Pick Claude Opus 4.5 if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if you want the cheaper token bill or you need the larger 256K context window.
Agentic
+8.1 difference
Coding
+5.9 difference
Knowledge
+19.5 difference
Inst. Following
+16.3 difference
Claude Opus 4.5
Hy3 Preview
$5 / $25
$0 / $0
46 t/s
N/A
1.01s
N/A
200K
256K
Pick Claude Opus 4.5 if you want the stronger benchmark profile. Hy3 Preview only becomes the better choice if you want the cheaper token bill or you need the larger 256K context window.
Claude Opus 4.5 is clearly ahead on the provisional aggregate, 77 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Opus 4.5's sharpest advantage is in knowledge, where it averages 66.2 against 46.7. The single biggest benchmark swing on the page is SWE-bench Verified, 80.9% to 74.4%.
Claude Opus 4.5 is also the more expensive model on tokens at $5.00 input / $25.00 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. Hy3 Preview is the reasoning model in the pair, while Claude Opus 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Hy3 Preview gives you the larger context window at 256K, compared with 200K for Claude Opus 4.5.
Claude Opus 4.5 is ahead on BenchLM's provisional leaderboard, 77 to 62. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 80.9% and 74.4%.
Claude Opus 4.5 has the edge for knowledge tasks in this comparison, averaging 66.2 versus 46.7. Inside this category, HLE is the benchmark that creates the most daylight between them.
Claude Opus 4.5 has the edge for coding in this comparison, averaging 65.9 versus 60. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude Opus 4.5 has the edge for agentic tasks in this comparison, averaging 62.5 versus 54.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Claude Opus 4.5 has the edge for instruction following in this comparison, averaging 79.4 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.