Claude 3.7 SonnetvsClaude Haiku 4.5
Claude 3.7 Sonnet | Claude Haiku 4.5 | |
|---|---|---|
| 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. | 49% | 77%Best |
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. | 62.3% | 73.3%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 68% | 73%Best |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Feb 24 2025 | Oct 15 2025 |
| Access | Proprietary | Proprietary |
Which is better: Claude 3.7 Sonnet or Claude Haiku 4.5?
Claude Haiku 4.5 leads Claude 3.7 Sonnet on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude 3.7 Sonnet shipped 233 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 3.7 Sonnet at 49%. On SWE-Bench Verified, Claude Haiku 4.5 leads at 73.3% vs Claude 3.7 Sonnet at 62.3%. On GPQA Diamond, Claude Haiku 4.5 leads at 73% vs Claude 3.7 Sonnet at 68%.
Frequently asked questions
Claude 3.7 Sonnet was released by Anthropic on Feb 24 2025.
Claude Haiku 4.5 was released by Anthropic on Oct 15 2025.
Claude Haiku 4.5 leads on SWE-Bench Verified — Claude 3.7 Sonnet 62.3% vs Claude Haiku 4.5 73.3%.
Claude Haiku 4.5 leads on GPQA Diamond — Claude 3.7 Sonnet 68% vs Claude Haiku 4.5 73%.