AI BENCHY
Advertise here
#41

GPT-5.6 Luna

OpenAI Release: 2026-07-09 Tested on: 2026-07-16 22:38 openai/gpt-5.6-luna::high
~400B total (~17B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

GPT-5.6 Luna scores 7.7 on AI BENCHY and ranks #41. It has 10.0 reliability, a 72.7% pass rate, $1.017 total cost, and 18.68s average response time.

What makes GPT-5.6 Luna unique: It stands out most in Domain specific, where it ranks #1, while Coding is its weakest area at #18.

Model facts

Researched on 2026-08-12

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 the architecture or count.

Parameter source Availability source

Score

7.7

Consistency

8.9

Reliability

10.0

Total Cost (Current Price)

$1.017

Total Output Tokens

155,998

Total Input Tokens

80,918

Input Price

$1.000 / 1M

Output Price

$6.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 72.7%

Flaky tests

3

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

Response Time (avg)

18.68s

Response Time (max): 111.09s

Response Time (total): 411.05s

Wrong answer: 7

Hamster playing table tennis

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

#41 GPT-5.6 Luna

high
Cost
$0.033
Time
34.2s
Tokens
5,484 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:21 Re-test 7.6 10.0 $0.090 ↓ Compare
2026-07-16 22:38 New test added 7.7 10.0 $1.017 Current run
2026-07-09 21:32 Initial run 7.7 10.0 $0.924 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-09 21:33 $1.000 / 1M $6.000 / 1M

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-5.6 LunahighvsDeepSeek V4 Flash 0423highGPT-5.6 LunahighvsSolar Pro 4xhighGPT-5.6 LunahighvsDeepSeek V4 ProhighGPT-5.6 LunahighvsNemotron 3 UltramediumFree AvailableGPT-5.6 LunahighvsClaude Opus 4.6mediumGPT-5.6 LunahighvsClaude Opus 5noneGPT-5.6 LunahighvsSeed-2.0-CodelowGPT-5.6 LunahighvsGPT-5.4 NanomediumGPT-5.6 LunahighvsGLM 5mediumGPT-5.6 LunahighvsGPT-5.6 Terralow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 5.5 4.7
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 5.0 10.0
Instructions following 9.9 10.0
Puzzle Solving 7.6 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models