readable AI benchmarks (simplified)

readable AI benchmarks

GPT-6 Luna (Xhigh) has a Quality Score of 33.5, ranking 133rd among 237 scored models. Per 1M tokens, pricing is $0.100 input, $0.500 output, $0.010 cached input, and $0.125 cache write. It has a 1M token context window. Its Reliability Score is 43.5, ranking 154th among 245 scored models, below average (total average: 46.4). Its Value Score is 30.6, around average compared with the total Value average of 28.3.

Quality Score33.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score30.6

Factual reliability43.5

Cache Discount90%

Model specification

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

Token prices USD per 1M tokens

Input: $0.100
Output: $0.500
Cached Input: $0.010
Cache write: $0.125
Cost per task: $0.104

Capability

Intelligence: 23.5
Omniscience (native net): -13.0
Correct: 38.6%
Blended price: $0.077

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.2%

Correct 38.6%Incorrect 51.6%Partial / not attempted 9.8%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1: 1235.5 Elo
AutomationBench-AA: 47.8%
GDP.pdf: 18.6%
FrontierCode v2.0: 18.4%
Terminal-Bench v4.0: 8.1%
AA-Omniscience v1.1: -13.0 native net
HLE-Diamond: 18.9%
CritPt v2 Hard: 37.0%
Terminal-Bench-Science v0.1.0: 5.2%

Standalone evaluations

GDPval-AA v2.1: 1372.5 Elo

Historical evaluations

SciCode v1.0.1: 51.7%
AA Long Context Reasoning v1.1: 80.0%
Humanity's Last Exam: 34.3%
CritPt: 17.4%
FrontierCode: 33.2%

Similar models

Graph Open on Artificial Analysis