readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Luna (low)

reasoning · closed weights · Sep 22, 2026

GPT-6 Luna (low) has a Quality Score of 37.4, ranking 83rd 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 45.4, ranking 95th among 282 scored models, above average (total average: 36.9). Its Value Score is 30.0, around average compared with the total Value average of 30.3.

Quality Score37.4coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score30.0
Reliability45.4
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
$0.0045

Capability

Intelligence
20.9
Coding
not available
Agentic
not available
Omniscience
-9.2
Correct
40.8%
Blended price
$0.077

Answer outcomes

Attempt rate: 90.7%

Correct 40.8%Incorrect 49.9%Abstained 9.3%

Artificial Analysis benchmarks

GDPval-AA v2
25%
SciCode
47%
Humanity’s Last Exam
20%
CritPt
3%
AA-Omniscience
45%
AA-LCR
74%

Similar models

Support me! Ko-Fi