readable AI benchmarks (simplified)

readable AI benchmarks

GPT-6 Luna (Low) has a Quality Score of 25.3, ranking 171st 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 41.0, ranking 165th among 245 scored models, below average (total average: 46.4). Its Value Score is 23.1, low compared with the total Value average of 28.3.

Quality Score25.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score23.1

Factual reliability41.0

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: $0.0051

Capability

Intelligence: 9.7
Omniscience (native net): -18.1
Correct: 36.1%
Blended price: $0.077

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.3%

Correct 36.1%Incorrect 54.2%Partial / not attempted 9.7%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1: 740.2 Elo
AutomationBench-AA: 12.0%
GDP.pdf: 9.0%
FrontierCode v2.0: 2.2%
Terminal-Bench v4.0: 0.0%
AA-Omniscience v1.1: -18.1 native net
HLE-Diamond: 10.2%
CritPt v2 Hard: 9.5%
Terminal-Bench-Science v0.1.0: 1.0%

Standalone evaluations

GDPval-AA v2.1: 1040.5 Elo

Historical evaluations

SciCode v1.0.1: 46.9%
AA Long Context Reasoning v1.1: 74.0%
Humanity's Last Exam: 20.3%
CritPt: 2.6%
FrontierCode: 14.1%

Similar models

Graph Open on Artificial Analysis