readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Luna (medium)

reasoning · closed weights · Sep 22, 2026

GPT-6 Luna (medium) has a Quality Score of 43.7, ranking 72nd 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 47.5, ranking 82nd among 282 scored models, above average (total average: 36.9). Its Value Score is 38.0, high compared with the total Value average of 30.3.

Quality Score43.7coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score38.0
Reliability47.5
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
$0.017

Capability

Intelligence
29.5
Coding
not available
Agentic
not available
Omniscience
-5.0
Correct
43.1%
Blended price
$0.077

Answer outcomes

Attempt rate: 91.3%

Correct 43.1%Incorrect 48.2%Abstained 8.7%

Artificial Analysis benchmarks

GDPval-AA v2
36%
SciCode
51%
Humanity’s Last Exam
28%
CritPt
11%
AA-Omniscience
47%
AA-LCR
78%

Similar models

Support me! Ko-Fi