MMODELYST
Models/Claude 3.5 Sonnet (June '24)
MDL

Claude 3.5 Sonnet (June '24)

Anthropic

Verified against Artificial Analysis · Jul 13, 2026
Capability
58
percentile index
Price /M
$3 / $15
in / out
Context
Avg score
47.2
5 benchmarks
AA Intelligence
8.3
index
Weights
Closed
Released
Jun 21, 2024
About

Claude 3.5 Sonnet (June '24) is a proprietary model in the Claude family from Anthropic. Benchmarked on 5 evals, averaging 47.2.

Benchmark scores · 5
avg 47.2 — higher is better
MMLU-Pro
75.1
MATH
69.5
GPQA Diamond
56
SciCode
31.6
Humanity's Last Exam
3.7
Details
PublisherAnthropic
FamilyClaude
Parameters
License
WeightsClosed
ReleasedJun 21, 2024
Performance & price
Price in / out$3 / $15 per 1M
Blended price$6 / 1M
Coding index26.0

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