MDL
Claude 3.7 Sonnet
Anthropic
Verified against Artificial Analysis · Jul 13, 2026
Capability
72
percentile index
Price /M
$0 / $0
in / out
Context
200K
tokens
Avg score
56.4
13 benchmarks
AA Intelligence
27.1
index
Weights
Closed
Released
Feb 24, 2025
About
Claude 3.7 Sonnet is a proprietary model in the Claude 3.7 family from Anthropic. Benchmarked on 13 evals, averaging 56.4.
proprietarytextvision
Benchmark scores · 13
avg 56.4 — higher is betterThe research behind this model
all papers mentioning it →RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuningMay 13, 2026Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought ReasoningMay 12, 2026Adversarial SQL Injection Generation with LLM-Based ArchitecturesMay 11, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Details
PublisherAnthropic
FamilyClaude 3.7
Parameters—
Licenseproprietary
WeightsClosed
ReleasedFeb 24, 2025
Performance & price
Price in / out$0 / $0 per 1M
Coding index36.4
Math index56.3
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Anthropic200K ctx · $15/M
Artificial Analysis$0/M