readable AI benchmarks (simplified)

readable AI benchmarks

Anthropic

Claude Sonnet 5.5 (High, Default Fallback)

reasoning · closed weights · Sep 28, 2026

Claude Sonnet 5.5 (High, Default Fallback) has a Quality Score of 50.4, ranking 72nd among 283 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.100 cached input, and $2.50 cache write. It has a 1M token context window. Its Reliability Score is 59.4, ranking 88th among 288 scored models, above average (total average: 48.2). Its Value Score is 33.7, around average compared with the total Value average of 29.3.

Quality Score50.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score33.7
Factual reliability59.4
Cache Discount95%

Model specification

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

Token prices USD per 1M tokens

Input
$2.00
Output
$10.00
Cached Input
$0.100
Cache write
$2.50
Cost per task
$1.64

Capability

Intelligence
41.5
Omniscience (native net)
18.7
Correct
50.3%
Blended price
$1.47

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 81.9%

Correct 50.3%Incorrect 31.6%Partial / not attempted 18.1%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1633.7 Elo
AutomationBench-AA
59.4%
private 657-task split from dataset v1.0.6
GDP.pdf
25.2%
FrontierCode v2.0
25.7%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
43.9%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
18.7 native net
HLE-Diamond
33.8%
CritPt v2 Hard
51.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
34.3%

Standalone evaluations

GDPval-AA v2.1
1551.3 Elo

Historical evaluations

SciCode v1.0.1
53.7%
AA Long Context Reasoning v1.1
78.0%
Humanity's Last Exam
45.8%
CritPt
24.6%
FrontierCode
44.3%

Similar models

Support me! Patreon