Head to head · tested 27 Oct 2026

Gemini 3.5 Flash Lite vs GPT-6 Luna: accuracy, speed and price

Similar accuracy; GPT-6 Luna costs less per question.

GoogleGemini 3.5 Flash Lite75.0% score · #15$0.0034 per question409 tok/s

OpenAIGPT-6 Luna72.5% score · #21$0.00025 per question137 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: Gemini 3.5 Flash Lite scored 75.0% and GPT-6 Luna 72.5% on the same 80 questions, a gap within what chance alone could produce.
GPT-6 Luna is 14× cheaper per question as billed ($0.00025 vs $0.0034), reasoning tokens included.
Gemini 3.5 Flash Lite generates text 3.0× faster: 409 tokens per second against 137.
Gemini 3.5 Flash Lite starts answering sooner: 1.1 s to the first token, against 1.2 s for GPT-6 Luna.

Which should you choose?

Choose Gemini 3.5 Flash Lite for faster streaming and a quicker first token. Choose GPT-6 Luna for the lower cost per correct answer ($0.00034 against $0.0045) and shorter outputs (about 431 tokens per question against 1,311).

Accuracy gap +2.5 points (z = 0.36). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	Gemini 3.5 Flash Lite	GPT-6 Luna	Edge
Verification scoreHigher is better	75.0%	72.5%	Too close to call
Cost per questionLower is better	$0.0034	$0.00025	GPT-6 Luna
Output speedHigher is better	409	137	Gemini 3.5 Flash Lite
Time to first tokenLower is better	1.1 s	1.2 s	Gemini 3.5 Flash Lite
End-to-end response timeLower is better	2.8 s	4.3 s	Gemini 3.5 Flash Lite
Tokens per questionLower is better	1,311	431	GPT-6 Luna
Context windowHigher is better	1M	1.1M	Similar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Gemini 3.5 Flash Lite first, GPT-6 Luna second

Verification scorehigher is better

Gemini 3.5 Flash Lite75.0%

GPT-6 Luna72.5%

Cost per questionlower is better

Gemini 3.5 Flash Lite$0.0034

GPT-6 Luna$0.00025

Output speedhigher is better

Gemini 3.5 Flash Lite409

GPT-6 Luna137

Time to first tokenlower is better

Gemini 3.5 Flash Lite1.1 s

GPT-6 Luna1.2 s

End-to-end response timelower is better

Gemini 3.5 Flash Lite2.8 s

GPT-6 Luna4.3 s

Tokens per questionlower is better

Gemini 3.5 Flash Lite1,311

GPT-6 Luna431

Context windowhigher is better

Gemini 3.5 Flash Lite1M

GPT-6 Luna1.1M

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	Gemini 3.5 Flash Lite	GPT-6 Luna
Science	30	23/30	25/30
Engineering	15	10/15	9/15
Medicine	11	7/11	6/11
Economics	9	7/9	7/9
Law	6	4/6	3/6
Humanities & social science	9	9/9	8/9
SuperGPQA dataset	50	33/50	33/50
MMLU-Pro dataset	30	27/30	25/30

Specifications and pricing

From OpenRouter's catalogue, plus our test dates

Specification	Gemini 3.5 Flash Lite	GPT-6 Luna
Creator	Google	OpenAI
Released	21 Jul 2026	22 Sept 2026
Weights	—	—
Reasoning	Yes	Yes
Input	text, image, video, file, audio	file, image, text
Output	text	text
Context window	1M tokens	1.1M tokens
Knowledge cutoff	—	—
List price in / out per 1M	$0.3 / $2.5	$0.1 / $0.5
Blended price per 1M (3:1)	$0.85	$0.20
Cheapest host	Google · $0.15 / $1.25	OpenAI · $0.05 / $0.25
Hosts on OpenRouter	2	3
Last tested	26 Oct 2026	25 Oct 2026

Compare any two models →

Gemini 3.5 Flash Lite vs GPT-6 Luna: frequently asked questions

Is Gemini 3.5 Flash Lite better than GPT-6 Luna?: On accuracy they are statistically tied: Gemini 3.5 Flash Lite scored 75.0% and GPT-6 Luna 72.5% on the same 80 questions from open datasets. Similar accuracy; GPT-6 Luna costs less per question.
Which is cheaper, Gemini 3.5 Flash Lite or GPT-6 Luna?: GPT-6 Luna is cheaper: $0.00025 per question as billed, against $0.0034. List prices: Gemini 3.5 Flash Lite $0.3 in / $2.5 out, GPT-6 Luna $0.1 in / $0.5 out per million tokens.
Which is faster, Gemini 3.5 Flash Lite or GPT-6 Luna?: Gemini 3.5 Flash Lite is faster at 409 output tokens per second, against 137. Time to first token: 1.1 s for Gemini 3.5 Flash Lite, 1.2 s for GPT-6 Luna.
Which has the larger context window, Gemini 3.5 Flash Lite or GPT-6 Luna?: Both accept about the same amount of context: 1M and 1.1M tokens.

Measure

Gemini 3.5 Flash Lite

GPT-6 Luna

Edge

Verification scoreHigher is better

75.0%

72.5%

Too close to call

Cost per questionLower is better

$0.0034

$0.00025

GPT-6 Luna

Output speedHigher is better

409

137

Gemini 3.5 Flash Lite

Time to first tokenLower is better

1.1 s

1.2 s

Gemini 3.5 Flash Lite

End-to-end response timeLower is better

2.8 s

4.3 s

Gemini 3.5 Flash Lite

Tokens per questionLower is better

1,311

431

GPT-6 Luna

Context windowHigher is better

1.1M

Similar

Subject

Questions

Gemini 3.5 Flash Lite

GPT-6 Luna

Science

23/30

25/30

Engineering

10/15

9/15

Medicine

7/11

6/11

Economics

7/9

Law

4/6

3/6

Humanities & social science

9/9

8/9

SuperGPQA dataset

33/50

MMLU-Pro dataset

27/30

25/30

Specification

Gemini 3.5 Flash Lite

GPT-6 Luna

Creator

Google

OpenAI

Released

21 Jul 2026

22 Sept 2026

Weights

—

Reasoning

Yes

Input

text, image, video, file, audio

file, image, text

Output

text

Context window

1M tokens

1.1M tokens

Knowledge cutoff

—

List price in / out per 1M

$0.3 / $2.5

$0.1 / $0.5

Blended price per 1M (3:1)

$0.85

$0.20

Cheapest host

Google · $0.15 / $1.25

OpenAI · $0.05 / $0.25

Hosts on OpenRouter

Last tested

26 Oct 2026

25 Oct 2026

Gemini 3.5 Flash Lite vs GPT-6 Luna: frequently asked questions

Is Gemini 3.5 Flash Lite better than GPT-6 Luna?

On accuracy they are statistically tied: Gemini 3.5 Flash Lite scored 75.0% and GPT-6 Luna 72.5% on the same 80 questions from open datasets. Similar accuracy; GPT-6 Luna costs less per question.

Which is cheaper, Gemini 3.5 Flash Lite or GPT-6 Luna?

GPT-6 Luna is cheaper: $0.00025 per question as billed, against $0.0034. List prices: Gemini 3.5 Flash Lite $0.3 in / $2.5 out, GPT-6 Luna $0.1 in / $0.5 out per million tokens.

Which is faster, Gemini 3.5 Flash Lite or GPT-6 Luna?

Gemini 3.5 Flash Lite is faster at 409 output tokens per second, against 137. Time to first token: 1.1 s for Gemini 3.5 Flash Lite, 1.2 s for GPT-6 Luna.

Which has the larger context window, Gemini 3.5 Flash Lite or GPT-6 Luna?

Both accept about the same amount of context: 1M and 1.1M tokens.

Gemini 3.5 Flash Lite vs GPT-6 Luna: accuracy, speed and price

Verdict

Which should you choose?

Head to head

Side by side

Every measure

Score vs. cost per question

Results by subject and dataset

Specifications and pricing

Related comparisons

Gemini 3.5 Flash Lite vs GPT-6 Luna: frequently asked questions

Gemini 3.5 Flash Lite vs GPT-6 Luna: accuracy, speed and price

Verdict

Which should you choose?

Head to head

Side by side

Every measure

Score vs. cost per question

Results by subject and dataset

Specifications and pricing

Related comparisons

Gemini 3.5 Flash Lite vs GPT-6 Luna: frequently asked questions