Claude Opus 5.5 is the stronger all-rounder.
Scores updated · 23 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 5.5 pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+25.1points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+10.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+4points ahead
Where Haiku 5.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5.5
- SWE-bench ProClaude Opus 5.5 by 25.189.964.8+25.1
- SWE-bench MultilingualClaude Opus 5.5 by 10.293.983.7+10.2
Other results20 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.
- Terminal-Bench-Science 0.1Claude Opus 5.5 by 38.158.720.6+38.1
- SWE-bench MultimodalClaude Opus 5.5 by 30.761.430.7+30.7
- Terminal-Bench 4.0Claude Opus 5.5 by 27.266.439.2+27.2
- GDPval-AA 2.1Claude Opus 5.5 by 226 rating points18461620+226 rating
- Election integrity multi-turn (appropriate response rate) - Claude.aiHaiku 5.5 by 138598+13
- Child safety multi-turn appropriate response rate (API, without a system prompt)Haiku 5.5 by 128496+12
- Election integrity multi-turn (appropriate response rate) - API, without a system promptHaiku 5.5 by 128799+12
- OSWorld 2.1Claude Opus 5.5 by 9.481.872.4+9.4
- Program BenchClaude Opus 5.5 by 9.291.282+9.2
- Suicide and self-harm multi-turn appropriate response rate (API, without a system prompt)Haiku 5.5 by 46670+4
- Suicide and self-harm multi-turn appropriate response rate (Claude.ai)Claude Opus 5.5 by 49490+4
- Suicide and self-harm single-turn requests posing potential risk harmless rate (API, without a system prompt)tie99.299.6tie
- Election integrity single-turn benign requests (refusal rate) - API, without a system prompttie00.3tie
- Election integrity single-turn benign requests (refusal rate) - Claude.aitie00.3tie
- Child safety multi-turn appropriate response rate (Claude.ai)tie9999tie
- Election integrity single-turn harmful requests (harmless rate) - API, without a system prompttie100100tie
- Election integrity single-turn harmful requests (harmless rate) - Claude.aitie100100tie
- Suicide and self-harm single-turn benign requests refusal rate (API, without a system prompt)tie00tie
- Suicide and self-harm single-turn benign requests refusal rate (Claude.ai)tie0.40.4tie
- Suicide and self-harm single-turn requests posing potential risk harmless rate (Claude.ai)tie100100tie
Questions people ask
Which is better, Claude Opus 5.5 or Haiku 5.5?
Claude Opus 5.5 wins all two areas where both have results: coding and reasoning. Haiku 5.5 wins none.
Which is better for coding?
Claude Opus 5.5. 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 23 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 20 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.