Claude 3.7 Sonnet (2025-02-19)

API ID claude-3-7-sonnet-20250219

claude-3-7-sonnet-20250219 was an Anthropic model, released February 2025.

Status: Retired
Released: February 2025
Shutdown: Feb 19, 2026
Replacement: Claude Sonnet 5.5claude-sonnet-5-5

claude-3-7-sonnet-20250219 stopped serving on February 19, 2026. Recommended replacement: claude-sonnet-5-5.

Benchmarks

Scores as each source published them

Comparing with Claude 3.5 Sonnet (2024-10-22), the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features

Arena

Arena	Claude 3.7 Sonnet (2025-02-19)	Claude 3.5 Sonnet (2024-10-22)	Change	Rank	Date	Source
Text Other settings 1372 ±4 vs 1374 ±3 By category Math 1385 rank 183 vs 1352 (+33) at thinking 32k (vs no setting) Creative writing 1393 rank 121 vs 1371 (+22) at thinking 32k (vs no setting) Instruction following 1411 rank 130 vs 1374 (+37) at thinking 32k (vs no setting) Hard prompts 1418 rank 164 vs 1399 (+19) at thinking 32k (vs no setting) Long prompts 1430 rank 131 vs 1396 (+34) at thinking 32k (vs no setting) Multi-turn 1400 rank 164 vs 1390 (+10, within range) at thinking 32k (vs no setting) Expert 1411 rank 165 vs 1372 (+39) at thinking 32k (vs no setting)	1388 ±4	1374 ±3	+14	178 of 415 38,159 votes	Oct 13, 2026	source
Text: Coding Other settings 1431 ±7 vs 1436 ±6	1452 ±8	1436 ±6	+16	154 of 410 6,135 votes	Oct 13, 2026	source
Vision Other settings 1175 ±9 vs 1160 ±8	1193 ±15	1160 ±8	+33	95 of 165 1,438 votes	Oct 9, 2026	source

Rated as claude-3-7-sonnet-20250219-thinking-32k; Claude 3.5 Sonnet (2024-10-22) as claude-3-5-sonnet-20241022. Some were rated at different settings; ratings on one arena share one scale, so the difference still reads directly. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

Benchmark	Claude 3.7 Sonnet (2025-02-19)	Claude 3.5 Sonnet (2024-10-22)	Change	Setting	Run	Source
GPQA Diamond Other settings 76.8% vs not run 32k 76.8% vs not run 16k 66.0% vs 55.3%	79.7%	55.3%	+24.4 pts	64k (vs no setting)	May 26, 2025	source
MATH Level 5 Other settings 90.0% vs not run 32k 86.3% vs not run 16k 68.2% vs 56.9%	91.2%	56.9%	+34.3 pts	64k (vs no setting)	Mar 13, 2025	source
OTIS Mock AIME 2024-2025 Other settings 53.3% vs not run 32k 46.7% vs not run 16k 21.9% vs 8.5%	57.8%	8.5%	+49.3 pts	64k (vs no setting)	Mar 13, 2025	source
SWE-bench Verified	61.0%	not run			Feb 4, 2026	source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

On cloud platforms

All platform dates

Platform	Platform ID	State	Shutdown	Time left	Replacement	Source
Google Cloud Vertex AI	claude-3-7-sonnet	Retired on May 11, 2026	May 11, 2026		—	source

Google Cloud Vertex AI retired this model 81 days after Anthropic's own API.

Read daily from each platform's own pages. The shutdown date and countdown on this page use Anthropic's own date.

Price history

USD per 1M tokens, standard tier

No price history yet.

Prices

USD per 1M tokens, every type and band, by tier

No published prices.

Changelog

Changes we detected on Anthropic's pages

No changes recorded yet.

Last checked Oct 15, 2026, 2:00 am ET · Sources: Anthropic models, Anthropic deprecations, Anthropic pricing, Anthropic model pages