AI BENCHY
Advertise here
#54

GPT-5.6 Luna

OpenAI Release: 2026-07-09 Tested on: 2026-07-09 21:16 openai/gpt-5.6-luna::medium
~400B total (~17B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

GPT-5.6 Luna scores 7.6 on AI BENCHY and ranks #54. It has 10.0 reliability, a 63.5% pass rate, $0.258 total cost, and 6.70s average response time.

What makes GPT-5.6 Luna unique: It stands out most in Combined, where it ranks #1, while Coding is its weakest area at #18. It is notably fast compared with similar models.

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

7.6

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$0.258

Total Output Tokens

36,888

Total Input Tokens

35,699

Input Price

$1.000 / 1M

Output Price

$6.000 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 63.5%

Flaky tests

1

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

Response Time (avg)

6.70s

Response Time (max): 29.85s

Response Time (total): 140.62s

Wrong answer: 8

Hamster playing table tennis

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

#54 GPT-5.6 Luna

medium
Cost
$0.014
Time
14.6s
Tokens
2,362 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:20 Re-test 7.4 10.0 $0.036 ↓ Compare
2026-07-16 22:37 New test added 7.6 10.0 $0.352 Compare
2026-07-09 21:16 Initial run 7.6 10.0 $0.258 Current run

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-07-09 21:16 · Initial run63/63 attempts7.69.610.013/21136,88835,699$0.2586.70s
2026-08-14 02:20 · Re-test66/66 attempts7.49.210.013/22244,52589,685$0.0367.43s
Difference—+0.1+0.40.00-1-7637-53986+$0.222-737ms

Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-09 21:18 $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 LunamediumvsKimi K2.7 CodemediumGPT-5.6 LunamediumvsLongCat 2.0mediumGPT-5.6 LunamediumvsQwen3.7 MaxnoneGPT-5.6 LunamediumvsQwen3.8 2.4T A95BhighGPT-5.6 LunamediumvsGemini 3.1 Flash Lite PreviewmediumGPT-5.6 LunamediumvsGrok 4.6lowGPT-5.6 LunamediumvsGrok Build 0.1mediumGPT-5.6 LunamediumvsGemini 3 Flash PreviewlowGPT-5.6 LunamediumvsGPT-5.4 MinimediumGPT-5.6 LunamediumvsClaude Sonnet 4.6none

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 5.4 7.2
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.1 10.0
Instructions following 9.9 10.0
Puzzle Solving 7.8 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models