readable AI benchmarks (simplified)

readable AI benchmarks

Anthropic

Claude 4 Sonnet (Reasoning)

reasoning · closed weights · May 22, 2025

Claude 4 Sonnet (Reasoning) has a Quality Score of 39.6, ranking 175th among 551 scored models. It has a 1M token context window. Its Reliability Score is 50.1, ranking 113th among 553 scored models, above average (total average: 35.6).

Quality Score39.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability50.1
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
18.9
Coding
not available
Agentic
not available
Omniscience
0.2
Correct
22.7%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 45.2%

Correct 22.7%Incorrect 22.5%Partial / not attempted 54.8%

Artificial Analysis benchmarks

GDPval-AA v2
9%
τ³-Banking
17%
Humanity’s Last Exam
11%
GPQA Diamond
78%
CritPt
0%
AA-Omniscience
50%
AA-LCR
70%

Similar models

Support me! Patreon