OpenRating is an independent, open-source AI rating platform. Join the community

OOpenRating
All models

OpenAI · Released Jul 9, 2026

GPT-5.6 Luna (Max)

Openai's reasoning-optimized model featuring verified performance on the OpenRating benchmark index, balanced for high throughput and cost efficiency.

Proprietary

OpenRating Index

24.0

0–100 composite

Reasoning Index

32.4

0–100 composite

Cost / Task

$0.33

benchmark run

Output speed

99 tok/s

blended tok/s

Time to first token

44.5s

median latency

Input price

$0.2

per 1M tokens

Output price

$1.2

per 1M tokens

Context window

1M

tokens

Strengths

  • Intelligence Index score of 24.0 on independent evaluations

  • 106.0 tokens/sec median generation throughput with sub-second response times

  • 1000k token context window supporting complex multi-document reasoning

How we rate GPT-5.6 Luna (Max)

OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.

OpenRating Index

24.0

Reasoning Index

32.4

Token Pricing

Input per 1M tokens

$0.2

Output per 1M tokens

$1.2

Cost of 1M input + 1M output

$1.4

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.33 total).

Reasoning (Chain of Thought)
$0.16
Answer generation
$0.053
Cache write overhead
$0.059
Cache hit queries
$0.030
Input payload
$0.030