Pass IndexThe State of AISign in

Claude 3.7 Sonnet

Claude 3.7 Sonnet was Anthropic's flagship model at release and the first hybrid reasoning model on the market, combining fast standard responses with an optional extended thinking mode.

text + image → text · made by Anthropic

$3→$15per Mtok in / out
Databricks · 6 sellers

Sold by 6 ways

SellerLaneRate
Databricks cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeraw.githubusercontent.com · read 2026-09-16
AWS Bedrock cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeraw.githubusercontent.com · read 2026-09-16
DigitalOcean cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writemodels.dev · read 2026-09-16
Snowflake Cortex cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cachedraw.githubusercontent.com · read 2026-09-16
Replicate aggregatorstandard$3per Mtok in$15per Mtok outreplicate.com · read 2026-08-25
DeepInfra aggregatorstandard$3.3per Mtok in$16.5per Mtok outapi.deepinfra.com · read 2026-08-25

Measured 31 standings

PlaceBoardMetricScore
3rdof 54Live bench — Epoch AIGlobal average76.1
4thof 81Forecastbench — Epoch AIOverall score61.8
4thof 16The agent company — Epoch AI% Score0.402
5thof 15Cad eval — Epoch AIOverall pass (%)0.54
5thof 8Spatialviz bench — Epoch AIOverall score0.339
6thof 22SWE-bench Multimodal% Resolved31.33
9thof 20Os world — Epoch AIScore35.8
10thof 25AgentBench Leaderboard (new)Success Rate (pass@1) AVG53.2
12thof 22Cybench — Epoch AIUnguided % Solved0.2
13thof 25AgentBench Leaderboard (new)Success Rate (pass@1) AVG (thinking)50
17thof 49Lech mazur writing — Epoch AIMean score8.11
19thof 69Aider polyglot coding leaderboardPercent correct64.9
20thof 108Math level 5 — Epoch AImean_score91.163
21stof 38Vpct — Epoch AICorrect0.39
23rdof 72Aider polyglot — Epoch AIPercent correct64.9
23rdof 42Fictionlivebench — Epoch AI120k token score0.531
24thof 50Metr time horizons — Epoch AIaverage_score0.6
27thof 46Enigma eval — Epoch AIAccuracy4.23
31stof 35Swe bench verified — Epoch AImean_score60.95
32ndof 41Deepresearchbench — Epoch AIAverage score0.436
32ndof 38Gso — Epoch AIScore OPT@10.038
34thof 51Humanity's Last Exam (Epoch AI replication)Accuracy8.04
59thof 102Simplebench — Epoch AIScore (AVG@5)0.464
75thof 101FrontierMath (Tiers 1-3)mean_score4.138
92ndof 152LMArena · VisionScore (Elo)1175
130thof 313GPQA Diamondmean_score78.504
166thof 290OTIS Mock AIME 2024-2025mean_score57.778
183rdof 402LMArena · TextScore (Elo)1372
187thof 244Arc agi — Epoch AIScore28.6
195thof 227Arc agi 2 — Epoch AIScore0.9
413thof 656Epoch capabilities index — Epoch AIECI Score141.19

About

Claude 3.7 Sonnet — a text model from Anthropic, sold by 6 companies from $3 in and $15 out per million tokens, placed 4th of 81 on Forecastbench — Epoch AI.

It takes text and images and returns text, with a context window of 200,000 tokens. It was published in February 2025, trained on material up to October 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Six companies sell it. The cheapest is $3 in and $15 out per million tokens at Databricks. It has been measured on 30 boards, and stands best at 4th of 81 on Forecastbench — Epoch AI.

Every current figure

Maker
Anthropic
Register
model
Takes
text + image
Returns
text
Context
200,000 tokens
Longest answer
64,000 tokens
Published
February 2025
Knowledge to
October 2024
Licence
not read
Sellers
6
Maker's own price
not read
Price
$3 in and $15 out per million tokens — Databricks
Boards
30
Best place
4th of 81 — Forecastbench — Epoch AI

Known as 8 names

Claude Sonnet 3.7 (2025-02-19)Claude Sonnet 3.7 Thinking (2025-02-19)claude-3-7-sonnet-20250219 (32k thinking tokens)claude-3-7-sonnet-20250219 (no thinking)OpenHands-Versa (Claude-3.7 Sonnet)Claude-Sonnet-3.7anthropic/claude-3-7-sonnet-latestanthropic/claude-3.7-sonnet