Model comparison

Gemini 3.6 Flash vs GPT-5.6 Luna

Google against OpenAI, compared on context, price, and attributed benchmark results.

Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

Google

Gemini 3.6 Flash

Balanced

OpenAI

GPT-5.6 Luna

Budget

AI model capability comparison
Specification	Gemini 3.6 Flash	GPT-5.6 Luna
Provider
Provider	Google	OpenAI
Tier
Tier	Balanced	Budget
Context window
Context window	1.05M	Winner: 1.05M
Max output
Max output	66K	Winner: 128K
Input / 1M tokens
Input / 1M tokens	$0.75	Winner: $0.20
Output / 1M tokens
Output / 1M tokens	$3.75	Winner: $1.20
Weights
Weights	Closed	Closed
Parameters
Parameters	Not verifiedUnverified	Not verifiedUnverified
Reasoning levels
Reasoning levels	minimal, low, medium, high	none, low, medium, high, xhigh, max
Modalities
Modalities	text, image, video, audio, pdf	text, image
API model id
API model id	gemini-3.6-flash	gpt-5.6-luna
Released
Released	July 21, 2026	July 9, 2026
Terminal-Bench 2.1 · source date Gemini 3.6 Flash: 2026-07
Terminal-Bench 2.1 · source date Gemini 3.6 Flash: 2026-07	78	Not verifiedUnverified
Terminal-Bench 2.1 · source date GPT-5.6 Luna: 2026-07-09
Terminal-Bench 2.1 · source date GPT-5.6 Luna: 2026-07-09	Not verifiedUnverified	84.7
DeepSWE 1.1 · source date Gemini 3.6 Flash: 2026-08
DeepSWE 1.1 · source date Gemini 3.6 Flash: 2026-08	48.6	Not verifiedUnverified
HLE-Verified · source date Gemini 3.6 Flash: 2026-08
HLE-Verified · source date Gemini 3.6 Flash: 2026-08	51.2	Not verifiedUnverified
LiveBench · source date GPT-5.6 Luna: 2026-09-05
LiveBench · source date GPT-5.6 Luna: 2026-09-05	Not verifiedUnverified	73.6

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Source date2026-09-05
LiveBench official leaderboard (benchmark-owned), max effort
Contamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes.
Comparable with caveatCompare only observations confirmed to use the same exact question-set version. Date proximity (including within one month) does not establish identical questions; when the version is unavailable, treat the scores as unaligned.
Source date2026-08
Google DeepMind model evaluation report (vendor; full 1,811-item HLE-Verified set) (Full 1,811-item verified/revised set; differs from original HLE and AA text-only HLE)
Expert reasoning on the verified and revised Humanity's Last Exam question set.
UnknownA distinct question set from original HLE and Artificial Analysis's text-only HLE. Shared dataset and publisher alone do not establish matching model effort, tools, filtering and run configuration; no quality winner is inferred without that evidence.
Source date2026-08
Google DeepMind August 3.7 evaluation report (quoting Datacurve for 3.6 Flash, 48.6%) (High thinking; quoted Datacurve result; July 3.6 report rounds to 49%)
Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.
Directly comparable
Source date2026-07-09
OpenAI GPT-5.6 launch table (vendor-reported; effort and experiment date unspecified) (Vendor launch table; complete common run settings unverified)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.
Source date2026-07
Google DeepMind model evaluation report (vendor, Terminus-2 harness)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.

Pricing tiers

Gemini 3.6 Flash: Intro Standard $0.75/$3.75 per MTok through December 31, 2026; $1.50/$7.50 from January 1, 2027. Output includes thinking tokens. Cached input $0.075, rising to $0.15; storage $0.50/MTok-hour, rising to $1. Batch/Flex input/output are $0.375/$1.875, rising to $0.75/$3.75. Priority $1.35/$6.75, rising to $2.70/$13.50. Grounding tools have separate charges and quotas; free-tier limits differ from paid.

GPT-5.6 Luna: Launch $1/$6, reduced to $0.20/$1.20 on July 30. Above 272K input the full request bills $0.40/$1.80. Cached input $0.02; cache writes $0.25 at short context. Batch $0.10/$0.60 at short context. Regional/FedRAMP processing adds 10% where eligible.

BalancedRecord checked October 1, 2026

Gemini 3.6 Flash

Gemini 3.6 Flash is Google's balanced multimodal Flash tier with a 1M-token context.

Best for

Multimodal pipelines
High-volume processing
Video and audio input

Watch out

An earlier Flash model, still listed as stable. Google reports improvements on selected tasks for later releases; that does not establish a quality increase for every workload. Thinking includes minimal through high; computer use is Preview. Intro pricing doubles January 1, 2027.

BudgetRecord checked October 1, 2026

GPT-5.6 Luna

OpenAI’s GPT-5.6 budget tier, succeeded by GPT-6 Luna on September 22. The newer model halves input pricing ($0.20→$0.10) and lowers output pricing from $1.20 to $0.50.

Best for

Classification
High-volume chat
Latency-sensitive pipelines

Watch out

Superseded by GPT-6 Luna and still listed in the API. Historical index captures are not current evidence of equal quality; the successor has lower Standard input and output prices.

When the cheaper one wins

GPT-5.6 Luna is cheaper on output at $1.20 per million tokens against $3.75 for Gemini 3.6 Flash — about 3.1×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, GPT-5.6 Luna is 67.2% Pass@1 at $3.03/task versus Gemini 3.6 Flash at 46.7% / $4.42/task. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
4/5 core specs verified on both sides — Not published for at least one side: parameter count.
No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Gemini 3.6 Flash: Google primary profile — whole-record source check October 1 (accessed 2026-10-01)
Gemini 3.6 Flash: Gemini current API pricing and cache-storage tiers (accessed 2026-10-01)
Gemini 3.6 Flash: Gemini thinking — model-specific Interactions levels (accessed 2026-10-01)
Gemini 3.6 Flash: Google — Gemini 3.6 Flash (accessed 2026-08-29)
Gemini 3.6 Flash: Google Cloud Gemini pricing (accessed 2026-08-29)
GPT-5.6 Luna: OpenAI model card — whole-profile source check October 1 (accessed 2026-10-01)
GPT-5.6 Luna: OpenAI current API pricing and processing tiers (accessed 2026-10-01)
GPT-5.6 Luna: OpenAI — GPT-5.6 (accessed 2026-08-29)
GPT-5.6 Luna: OpenAI API pricing (gpt-5.6-luna $0.20/$1.20) (accessed 2026-08-29)
GPT-5.6 Luna: OpenAI — Introducing GPT-6 Sol and Luna (GPT-5.6 Luna successor) (accessed 2026-09-26)

Related comparisons

Diving deeper on one model? Gemini 3.6 Flash · GPT-5.6 Luna

Common questions

Gemini 3.6 Flash vs GPT-5.6 Luna

Answered from the verified figures on this page rather than general guidance.

Is Gemini 3.6 Flash or GPT-5.6 Luna cheaper for input?

GPT-5.6 Luna is cheaper at $0.20 per million input tokens, against $0.75 for Gemini 3.6 Flash — roughly 3.8× the price. Estimate both input and output token volume for your workload. These are base rates; Gemini 3.6 Flash: Intro Standard $0.75/$3.75 per MTok through December 31, 2026; $1.50/$7.50 from January 1, 2027. Output includes thinking tokens. Cached input $0.075, rising to $0.15; storage $0.50/MTok-hour, rising to $1. Batch/Flex input/output are $0.375/$1.875, rising to $0.75/$3.75. Priority $1.35/$6.75, rising to $2.70/$13.50. Grounding tools have separate charges and quotas; free-tier limits differ from paid. GPT-5.6 Luna: Launch $1/$6, reduced to $0.20/$1.20 on July 30. Above 272K input the full request bills $0.40/$1.80. Cached input $0.02; cache writes $0.25 at short context. Batch $0.10/$0.60 at short context. Regional/FedRAMP processing adds 10% where eligible.

Is Gemini 3.6 Flash or GPT-5.6 Luna cheaper for output?

GPT-5.6 Luna is cheaper at $1.20 per million output tokens, against $3.75 for Gemini 3.6 Flash — roughly 3.1× the price. Estimate both input and output token volume for your workload. These are base rates; Gemini 3.6 Flash: Intro Standard $0.75/$3.75 per MTok through December 31, 2026; $1.50/$7.50 from January 1, 2027. Output includes thinking tokens. Cached input $0.075, rising to $0.15; storage $0.50/MTok-hour, rising to $1. Batch/Flex input/output are $0.375/$1.875, rising to $0.75/$3.75. Priority $1.35/$6.75, rising to $2.70/$13.50. Grounding tools have separate charges and quotas; free-tier limits differ from paid. GPT-5.6 Luna: Launch $1/$6, reduced to $0.20/$1.20 on July 30. Above 272K input the full request bills $0.40/$1.80. Cached input $0.02; cache writes $0.25 at short context. Batch $0.10/$0.60 at short context. Regional/FedRAMP processing adds 10% where eligible.

Which has the larger context window, Gemini 3.6 Flash or GPT-5.6 Luna?

Both accept about 1.05M tokens of context, so document length will not decide between them.

Do Gemini 3.6 Flash and GPT-5.6 Luna support the same reasoning levels?

Gemini 3.6 Flash exposes minimal, low, medium, high, while GPT-5.6 Luna exposes none, low, medium, high, xhigh, max.

Should I use Gemini 3.6 Flash or GPT-5.6 Luna?

We classify Gemini 3.6 Flash in the balanced tier and GPT-5.6 Luna in the budget tier. Test whether either meets your accuracy, tool-use and latency requirements before choosing on price.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: GPT-5.6 Luna costs $0.20 per 1M tokens versus $0.75 for Gemini 3.6 Flash — a 3.8x difference at the headline tier.
Context: GPT-5.6 Luna takes 1.05M against 1.05M for Gemini 3.6 Flash — only decisive if your prompts approach the smaller window.
Positioning: Gemini 3.6 Flash sits in the balanced tier, GPT-5.6 Luna in the budget tier. Compare accuracy, reliability, latency, and cost on representative tasks before choosing.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.