MMODELYST
Models/Claude 4 Sonnet
MDL

Claude 4 Sonnet

Anthropic

Verified against Artificial Analysis · Jul 13, 2026
Capability
78
percentile index
Price /M
$3 / $15
in / out
Context
Avg score
60.5
11 benchmarks
AA Intelligence
28.9
index
Weights
Closed
Released
May 22, 2025
About

Claude 4 Sonnet is a proprietary model in the Claude family from Anthropic. Benchmarked on 11 evals, averaging 60.5.

Benchmark scores · 11
avg 60.5 — higher is better
MATH
99.1
MMLU-Pro
84.2
GPQA Diamond
77.7
AIME
74.3
LiveCodeBench
65.5
AA Long-Context Reasoning
64.7
τ²-bench
64.6
IFBench
54.7
SciCode
40
Terminal-Bench Hard
31.1
Humanity's Last Exam
9.6
Details
PublisherAnthropic
FamilyClaude
Parameters
License
WeightsClosed
ReleasedMay 22, 2025
Performance & price
Price in / out$3 / $15 per 1M
Blended price$6 / 1M
Coding index37.6
Math index74.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$15/M