Claude Haiku 4.5vsClaude Sonnet 4
Claude Haiku 4.5 | Claude Sonnet 4 | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 77%Best | 30% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 73.3%Best | 72.7% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 73% | 75.4%Best |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Oct 15 2025 | May 22 2025 |
| Access | Proprietary | Proprietary |
Which is better: Claude Haiku 4.5 or Claude Sonnet 4?
Claude Haiku 4.5 leads Claude Sonnet 4 on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude Sonnet 4 shipped 146 days before Claude Haiku 4.5, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, Claude Haiku 4.5 leads at 77% vs Claude Sonnet 4 at 30%. On SWE-Bench Verified, Claude Haiku 4.5 leads at 73.3% vs Claude Sonnet 4 at 72.7%. On GPQA Diamond, Claude Sonnet 4 leads at 75.4% vs Claude Haiku 4.5 at 73%.
Frequently asked questions
Claude Haiku 4.5 was released by Anthropic on Oct 15 2025.
Claude Sonnet 4 was released by Anthropic on May 22 2025.
Claude Haiku 4.5 leads on SWE-Bench Verified — Claude Haiku 4.5 73.3% vs Claude Sonnet 4 72.7%.
Claude Sonnet 4 leads on GPQA Diamond — Claude Haiku 4.5 73% vs Claude Sonnet 4 75.4%.