readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Luna (xhigh)

reasoning · closed weights · Sep 22, 2026

GPT-6 Luna (xhigh) has a Quality Score of 47.4, ranking 59th among 282 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 49.1, ranking 72nd among 282 scored models, above average (total average: 36.9). Its Value Score is 42.1, high compared with the total Value average of 30.3.

Quality Score47.4coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score42.1
Reliability49.1
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
33.9
Coding
not available
Agentic
not available
Omniscience
-1.8
Correct
44.2%
Blended price
$0.077

Answer outcomes

Attempt rate: 90.2%

Correct 44.2%Incorrect 46.0%Abstained 9.8%

Artificial Analysis benchmarks

GDPval-AA v2
40%
SciCode
52%
Humanity’s Last Exam
34%
CritPt
17%
AA-Omniscience
49%
AA-LCR
80%

Similar models

Support me! Ko-Fi