MDL
Claude Sonnet 5
Anthropic
Verified against Artificial Analysis · Jul 13, 2026
Capability
97
percentile index
Price /M
$2 / $10
in / out
Context
1M
tokens
Avg score
63.8
4 benchmarks
AA Intelligence
53.4
index
Speed
79 tok/s
TTFT 1m 49s
Released
Jun 30, 2026
About
Claude Sonnet 5 is a proprietary model in the Claude family from Anthropic. Benchmarked on 4 evals, averaging 63.8.
Benchmark scores · 4
avg 63.8 — 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 speed79 tok/s
Latency (TTFT)1m 49s
Price in / out$2 / $10 per 1M
Blended price$4 / 1M
Coding index71.5
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
AA Long-Context Reasoningfirst seen at 70.7
11d ago
SciCodefirst seen at 53.6
11d ago
Humanity's Last Examfirst seen at 39.6
11d ago
GPQA Diamondfirst seen at 91.1
11d ago
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$10/M