Claude Haiku 5.5 vs Claude Sonnet 5.5
Claude Haiku 5.5 Verdict
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 61.3.
- Claude Sonnet 5.5 (max) is stronger in coding, composite, knowledge, long context, maths, reasoning, agents & tools.
- Claude Haiku 5.5 (high) is 20× cheaper ($0.200 vs $4.00 per 1M blended).
| Metric | Claude Haiku 5.5 (high) | Claude Sonnet 5.5 (max) |
|---|---|---|
| BenchLeader Index | 61.3 | 67.6 |
| Coding score | 62.6 | 69.8 |
| Composite score | 72.4 | 72.6 |
| Knowledge score | 64.3 | 65.4 |
| Long context score | 63.8 | 66.6 |
| Maths score | 66.2 | 72.9 |
| Reasoning score | 72.1 | 81.1 |
| Agents & tools score | – | 69.5 |
| Blended price $/M | $0.200 | $4.00 |
| Output speed | 174 tok/s | 141 tok/s |
| Time to first answer | 22.6 s | 487.1 s |
| Context window | 1M | 1M |
| GPQA Diamond | – | 95.6% |
| FrontierMath Tiers 1–3 | – | 88.8% |
| FrontierMath Tier 4 | – | 80.5% |
| OTIS Mock AIME | 97.2% | 100.0% |
| SimpleQA Verified | – | 46.5% |
| Terminal-Bench | – | 61.8% |
| SciCode | – | 61.0% |
| APEX-Agents | – | 75.5% |
| ProofBench | – | 100.0% |
| LMArena WebDev | 1587 | – |
| LMArena Agent | – | 12 |
| LiveBench | – | 75.7% |
| LiveBench Reasoning | – | 91.6% |
| LiveBench Coding | – | 91.4% |
| LiveBench Agentic Coding | – | 56.3% |
| LiveBench Mathematics | – | 96.1% |
| LiveBench Data Analysis | – | 59.5% |
| LiveBench Language | – | 78.0% |
| LiveBench Instruction Following | – | 56.8% |
| AA Intelligence Index v4.3.2 | 37.8 | 56 |
| AA-LCR | 77.3% | 82.7% |
| AA-Omniscience | 5.8 | 32.3 |
| Humanity's Last Exam (AA) | 37.3% | 55.0% |
| SciCode (AA) | 48.7% | 61.0% |
| CritPt | 18.6% | 31.4% |
| GDPval-AA v2.1 | 45.9% | 67.0% |
| Analyst Agent (AA) | – | 57.5% |
| Mystery Game Puzzles | – | 65.0% |
| CursorBench | – | 55.5% |
| FrontierSWE | – | 61.9% |
| Terminal-Bench 4.0 (AA) | 21.7% | 63.6% |
| AutomationBench | 33.7% | 71.8% |
| GDP.pdf | 17.2% | 25.8% |
| MLCR | – | 75.0% |
| Harvey LAB | 1.1% | 2.8% |
| AA-Omniscience: accuracy | 34.8% | 54.0% |
| AA-Omniscience: non-hallucination | 55.5% | 53.0% |
| AA-Briefcase v1.1 | 1442 | 1823 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Haiku 5.5 vs Claude Sonnet 5.5: questions
- Is Claude Haiku 5.5 better than Claude Sonnet 5.5?
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 61.3. The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5.5 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Haiku 5.5 better than Claude Sonnet 5.5 for coding?
- Claude Sonnet 5.5 scores higher in coding (70 vs 63 on the category index, where 50 is average).
- Which is cheaper, Claude Haiku 5.5 or Claude Sonnet 5.5?
- Claude Haiku 5.5 is cheaper: $0.200 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Haiku 5.5 or Claude Sonnet 5.5?
- Claude Haiku 5.5 streams faster: 174 against 141 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.