Advertise here
#260

GPT-6 Luna

OpenAI Release: 2026-09-23 Tested on: 2026-09-23 05:09 openai/gpt-6-luna::none
~400B total (~17B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

GPT-6 Luna scores 5.6 on AI BENCHY and ranks #260. It has 9.9 reliability, a 42.4% pass rate, $0.012 total cost, and 19.08s average response time.

What makes GPT-6 Luna unique: It stands out most in Puzzle Solving, where it ranks #3, while Instructions following is its weakest area at #10.

Model facts

Researched on 2026-09-23

Estimated
Parameters
~400B total (~17B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose parameter counts or architecture. Low-confidence catalog estimate carries forward the prior openai/gpt-5.6-luna family estimate; the linked announcement establishes identity and availability, not these counts.

Parameter source Availability source

Score

5.6

Consistency

8.1

Reliability

9.9

Total Cost (Current Price)

$0.012

Total Output Tokens

5,508

Total Input Tokens

87,216

Input Price

$0.100 / 1M

Output Price

$0.500 / 1M

Tests Correct

Wrong Tests: 15

Attempt pass rate: 42.4%

Flaky tests

5

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

19.08s

Response Time (max): 98.62s

Response Time (total): 419.83s

Wrong answer: 13 API error: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#260 GPT-6 Luna

none
Cost
$0.002
Time
26.0s
Tokens
3,235 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GPT-6 LunanonevsKAT-Coder-Air V2.5highGPT-6 LunanonevsGemma 4 26B A4BnoneFree AvailableGPT-6 LunanonevsQwen3.5-122B-A10BnoneGPT-6 LunanonevsKAT-Coder-Air V2.5mediumGPT-6 LunanonevsKimi K2.6noneGPT-6 LunanonevsNemotron 3.5 LightninghighFree AvailableGPT-6 LunanonevsGLM 5.1noneGPT-6 LunanonevsHy4 previewlowGPT-6 LunanonevsLing-3.0-flashnoneGPT-6 LunanonevsQwen3.6 27Bnone

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 4.8 10.0
Coding 5.5 10.0
Combined 3.8 5.8
Data parsing and extraction 7.3 5.9
Domain specific 5.3 7.2
General Intelligence 5.1 10.0
Instructions following 6.2 5.8
Puzzle Solving 5.4 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models