readable AI benchmarks (simplified)

readable AI benchmarks

Grok 4.7 (Xhigh) has a Quality Score of 50.6, ranking 48th among 235 scored models. Per 1M tokens, pricing is $2.00 input, $6.00 output, and $0.500 cached input. It accepts text, image, and pdf input, outputs text, and has a 500k token context window. Its Reliability Score is 65.6, ranking 27th among 242 scored models, above average (total average: 46.3). Its Value Score is 34.1, high compared with the total Value average of 28.2.

Quality Score50.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score34.1

Factual reliability65.6

Cache Discount75%

Model specification

Reasoning: reasoning
Input modalities: text, image, pdf
Output modalities: text
Context window: 500k tokens
Weights: closed weights

Token prices USD per 1M tokens

Input: $2.00
Output: $6.00
Cached Input: $0.500
Cache write: not available
Cost per task: $7.77

Capability

Intelligence: 35.5
Omniscience (native net): 31.2
Correct: 42.7%
Blended price: $1.35

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 54.2%

Correct 42.7%Incorrect 11.5%Partial / not attempted 45.8%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1: 1637.4 Elo
AutomationBench-AA: 65.6%
GDP.pdf: 20.0%
FrontierCode v2.0: 28.7%
Terminal-Bench v4.0: 25.8%
AA-Omniscience v1.1: 31.2 native net
HLE-Diamond: 23.2%
CritPt v2 Hard: 33.5%
Terminal-Bench-Science v0.1.0: 11.4%

Standalone evaluations

GDPval-AA v2.1: 1718.4 Elo

Historical evaluations

SciCode v1.0.1: 57.4%
AA Long Context Reasoning v1.1: 76.7%
Humanity's Last Exam: 43.1%
CritPt: 17.7%
FrontierCode: 33.8%

Similar models

Graph Open on Artificial Analysis