The two are evenly matched.Haiku 5.5 is better at reasoning; Claude Opus 5 at coding.
Scores updated · 9 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Reasoning rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 5 pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+14.4points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+5.8points ahead
Where Haiku 5.5 pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.5points ahead
Every test, side by side
All 9 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5
- SWE-bench ProClaude Opus 5 by 14.464.879.2+14.4
- SWE-bench MultilingualClaude Opus 5 by 5.883.789.5+5.8
Other results6 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- SWE-bench MultimodalClaude Opus 5 by 28.730.759.4+28.7
- Terminal-Bench 4.0Claude Opus 5 by 12.639.251.8+12.6
- GDPval-AA 2.1Claude Opus 5 by 88 rating points16201708+88 rating
- Terminal-Bench-Science 0.1Claude Opus 5 by 8.420.629+8.4
- HealthBench Professional length-adjustedHaiku 5.5 by 564.859.8+5
- Program BenchClaude Opus 5 by 3.48285.4+3.4
Questions people ask
Which is better, Haiku 5.5 or Claude Opus 5?
Haiku 5.5 and Claude Opus 5 each win one of the two areas where both have results. Haiku 5.5 wins reasoning; Claude Opus 5 wins coding.
Which is better for coding?
Claude Opus 5. It wins 2 of the 2 coding tests both models report; Haiku 5.5 wins none.
How do you compare the two?
We use the 9 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.