Claude 3.7 SonnetvsClaude Opus 4.6
Claude 3.7 Sonnet | Claude Opus 4.6 | |
|---|---|---|
| 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. | — | $5.00 |
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. | — | $25.00 |
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. | — | $0.50 |
| 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. | 49% | 87% |
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. | 62.3% | 80.8% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 68% | 91.3% |
| 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. | — | 75% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 83.7% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 53% |
Arena Elo (Text)Community preference — Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | — | 1504 |
Arena Elo (Code)Community preference (code) — Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1543 |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Feb 24 2025 | Feb 5 2026 |
| Access | Proprietary | Proprietary |
Frequently asked questions
Claude Opus 4.6 leads Claude 3.7 Sonnet on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Only Claude Opus 4.6 has a verified first-party API price: $5.00 per million input tokens and $25.00 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.7 Sonnet. Claude 3.7 Sonnet shipped 346 days before Claude Opus 4.6, 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 Opus 4.6 leads at 87% vs Claude 3.7 Sonnet at 49%. On SWE-Bench Verified, Claude Opus 4.6 leads at 80.8% vs Claude 3.7 Sonnet at 62.3%. On GPQA Diamond, Claude Opus 4.6 leads at 91.3% vs Claude 3.7 Sonnet at 68%.
Claude 3.7 Sonnet was released by Anthropic on Feb 24 2025.
Claude Opus 4.6 was released by Anthropic on Feb 5 2026.
Claude Opus 4.6 leads on SWE-Bench Verified — Claude 3.7 Sonnet 62.3% vs Claude Opus 4.6 80.8%.
Claude Opus 4.6 leads on GPQA Diamond — Claude 3.7 Sonnet 68% vs Claude Opus 4.6 91.3%.
Only Claude Opus 4.6 has a verified first-party API price: $5.00 per million input tokens and $25.00 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.7 Sonnet. Rates are pay-as-you-go API prices verified on August 18, 2026.