readable AI benchmarks (simplified)

readable AI benchmarks

GPT-6 Luna (Medium) has a Quality Score of 30.8, ranking 152nd 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 43.2, ranking 156th among 245 scored models, below average (total average: 46.4). Its Value Score is 28.2, around average compared with the total Value average of 28.3.

Quality Score30.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score28.2

Factual reliability43.2

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: $0.042

Capability

Intelligence: 18.5
Omniscience (native net): -13.6
Correct: 38.7%
Blended price: $0.077

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 91.0%

Correct 38.7%Incorrect 52.3%Partial / not attempted 9.0%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1: 1096.1 Elo
AutomationBench-AA: 40.5%
GDP.pdf: 13.8%
FrontierCode v2.0: 12.8%
Terminal-Bench v4.0: 2.5%
AA-Omniscience v1.1: -13.6 native net
HLE-Diamond: 15.1%
CritPt v2 Hard: 27.5%
Terminal-Bench-Science v0.1.0: 1.4%

Standalone evaluations

GDPval-AA v2.1: 1270.5 Elo

Historical evaluations

SciCode v1.0.1: 50.9%
AA Long Context Reasoning v1.1: 78.3%
Humanity's Last Exam: 28.3%
CritPt: 10.6%
FrontierCode: 31.8%

Similar models

Graph Open on Artificial Analysis