← All benchmarks

Claude 3.7 Sonnet (Reasoning)

Anthropic · Released 2025-02-24 · Independent benchmark scores from Artificial Analysis

Intelligence Index
27.1
Output speed
0.0
tokens/sec
Blended price
$0.00
per 1M tokens
Time to first token
0.00s

Model metadata

Model ID13358187-4584-479c-ab43-5bcdf8f297a4
Slugclaude-3-7-sonnet-thinking
Release date2025-02-24
ProviderAnthropic
Provider sluganthropic
Output speed0.0 tok/s
Time to first token0.00s
Time to first answer0.00s
Blended price ($/1M)$0.00
Input price ($/1M)$0.00
Output price ($/1M)$0.00

All evaluation scores (17)

aime48.7%
aime 2556.3%
artificial analysis coding index36.40
artificial analysis intelligence index27.10
artificial analysis math index56.30
gpqa77.2%
hle10.3%
ifbench48.3%
lcr60.7%
livecodebench47.3%
math 50094.7%
mmlu pro83.7%
scicode40.3%
tau banking
tau254.7%
terminalbench hard21.2%
terminalbench v2 1

Source: artificialanalysis.ai/models/claude-3-7-sonnet-thinking

Benchmark data from Artificial Analysis.