MDL
Claude Sonnet 4.6
Anthropic
Verified against Artificial Analysis · Jul 13, 2026
Capability
87
percentile index
Price /M
$3 / $15
in / out
Context
1M
tokens
Avg score
60.0
7 benchmarks
AA Intelligence
47.2
index
Speed
66 tok/s
TTFT 1m 21s
Released
Feb 17, 2026
About
Claude Sonnet 4.6 is a proprietary model in the Claude family from Anthropic. Benchmarked on 7 evals, averaging 60.0.
Benchmark scores · 7
avg 60.0 — higher is betterThe research behind this model
all papers mentioning it →DEI: Diversity in Evolutionary Inference for Quality-Diversity Search▲ 14 on HF · May 26, 2026PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents▲ 8 on HF · Jun 28, 2026Hierarchical Experimentalist Agents▲ 5 on HF · Jun 28, 2026τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems▲ 1 on HF · Jun 8, 2026How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing ConsistencyMay 28, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed66 tok/s
Latency (TTFT)1m 21s
Price in / out$3 / $15 per 1M
Blended price$6 / 1M
Coding index63.0
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
Artificial Analysis$15/M