Claude 3.5 HaikuvsClaude Sonnet 4.5
Claude 3.5 Haiku | Claude Sonnet 4.5 | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $3.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $15.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.30 |
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given 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. | 50% | 79% |
SWE-Bench VerifiedCoding — Real 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. | 40.6% | 77.2% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 41.6% | 83.4% |
| BenchmarksPublished by one model only | ||
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 50% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 68% |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Oct 22 2024 | Sep 29 2025 |
| Access | Proprietary | Proprietary |
Frequently asked questions
Claude Sonnet 4.5 leads Claude 3.5 Haiku on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Only Claude Sonnet 4.5 has a verified first-party API price: $3.00 per million input tokens and $15.00 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Claude 3.5 Haiku shipped 342 days before Claude Sonnet 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 Sonnet 4.5 leads at 79% vs Claude 3.5 Haiku at 50%. On SWE-Bench Verified, Claude Sonnet 4.5 leads at 77.2% vs Claude 3.5 Haiku at 40.6%. On GPQA Diamond, Claude Sonnet 4.5 leads at 83.4% vs Claude 3.5 Haiku at 41.6%.
Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.
Claude Sonnet 4.5 was released by Anthropic on Sep 29 2025.
Claude Sonnet 4.5 leads on SWE-Bench Verified — Claude 3.5 Haiku 40.6% vs Claude Sonnet 4.5 77.2%.
Claude Sonnet 4.5 leads on GPQA Diamond — Claude 3.5 Haiku 41.6% vs Claude Sonnet 4.5 83.4%.
Only Claude Sonnet 4.5 has a verified first-party API price: $3.00 per million input tokens and $15.00 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Rates are pay-as-you-go API prices verified on August 18, 2026.