Skip to main content

OpenAIGoogleLLM matchup

GPT-5.6 Terravs.Gemini 3.6 Flash

Which one is better?

GPT-5.6 Terra and Gemini 3.6 Flash perform about equally well, but GPT-5.6 Terra costs 2.7 times (input) and 3.2 times (output) as much.

level
IntelligenceOverall index, 100 points = average
100.9

GPT-5.6 Terra

Rank 31

97.2

Gemini 3.6 Flash

Rank 38

Gemini 3.6 Flash faster
SpeedTokens per second
77

GPT-5.6 Terra

114

Gemini 3.6 Flash

Gemini 3.6 Flash cheaper
Price$ per 1M tokens
$4.50

GPT-5.6 Terra

$1.50

Gemini 3.6 Flash

Above 272,000 tokens of context, GPT-5.6 Terra costs more: $4 input and $18 output per 1M tokens.

Choose GPT-5.6 Terra for

GeneralCodingFinanceLegal (not certain)

Choose Gemini 3.6 Flash for

KnowledgeMultimodal (not certain)Health (not certain)

Where is the difference?

Strengths at a glance

GPT-5.6 TerraGemini 3.6 FlashMedian of all ranked models

9010011080CodingGPT-5.6 TerraReasoninglevelKnowledgeGemini 3.6FlashGeneralGPT-5.6 TerraMultimodalslightlyGemini 3.6FlashFinanceGPT-5.6 TerraLegalslightlyGPT-5.6 TerraHealthslightlyGemini 3.6Flash
CodingGPT-5.6 Terra ahead
GPT-5.6 Terra104.5Rank 23
Gemini 3.6 Flash91.3Rank 52
Median of ranked models87.5

95 % range: GPT-5.6 Terra 99.0 to 110.1, Gemini 3.6 Flash 86.8 to 95.7.

AreaGPT-5.6 TerraGemini 3.6 Flash

The same values and verdicts as the bars below. In the close-up the net starts at 80 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Mathematics, Agents.

GPT-5.6 Terra is ahead in 3 of 10 areas, Gemini 3.6 Flash in 1.

GPT-5.6 Terra ahead: 3GPT-5.6 Terra slightly ahead: 1level: 1too little data: 2Gemini 3.6 Flash slightly ahead: 2Gemini 3.6 Flash ahead: 1

Areas in the overall index
KnowledgeGemini 3.6 Flash +1988.1 to 107.4
GeneralGPT-5.6 Terra +15104.8 to 90.1
CodingGPT-5.6 Terra +13104.5 to 91.3
Multimodalleaning Gemini 3.6 Flashnot certain · 3 tests each
Reasoninglevel105.7 to 103.2
Agentstoo little data101.7 to 93.0
Mathematicstoo little data101.8 to 93.5
Specialist fields
FinanceGPT-5.6 Terra +6102.4 to 96.0
Legalleaning GPT-5.6 Terranot certain · 2 tests each
Healthleaning Gemini 3.6 Flashnot certain · 2 tests each

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 3 more areas that do not count toward the overall index
Cybersecuritytoo little data107.3 to 79.5
Productivitytoo little data97.9 to 84.6
Educationonly GPT-5.6 Terra has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeGPT-5.6 TerraCoding 104.5 to 91.3
Maths and data analysislevelMathematics 101.8 to 93.5 (too little data), Reasoning 105.7 to 103.2
Facts and researchGemini 3.6 FlashKnowledge 88.1 to 107.4
Agents and workflowsopenAgents 101.7 to 93.0 (too little data)
Fast chat repliesGemini 3.6 Flash77 to 114 tokens per second
Security analysisopenCybersecurity 107.3 to 79.5 (too little data)
Many requests on a small budgetGemini 3.6 Flash$4.50 to $1.50 per 1M tokens
Finance, legal and medical textsdepends on the partFinance 102.4 to 96.0, Legal 102.7 to 93.3, Health 94.8 to 98.6
Images, screenshots and PDFsleaning Gemini 3.6 FlashMultimodal 99.3 to 103.2

GPT-5.6 Terra vs. Gemini 3.6 Flash in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

GPT-5.6 Terra

GPT-5.6 Terra: Pelican on a bicycle
A community classic for free-form SVG drawing.

Sep 7, 2026 · 65 s · $0.04

Test details
Run date
Sep 7, 2026
API provider
openrouter
Requested API model
openai/gpt-5.6-terra
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,373 tokens
Cost of the attempt
$0.0405
Response time
64.6 s
API model reported in response
openai/gpt-5.6-terra
Pinned endpoint
OpenAI | openai/gpt-5.6-terra-20260709
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Gemini 3.6 Flash

The response reached the token limit. No complete recording is available.

Oct 5, 2026 · 40 s · $0.03

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.6-flash
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,188 tokens
Cost of the attempt
$0.0307
Response time
39.6 s
API model reported in response
google/gemini-3.6-flash
Pinned endpoint
Google AI Studio | google/gemini-3.6-flash-20260721
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed

Earlier attempts (3)

  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

GPT-5.6 Terra

Unavailable in this round

Gemini 3.6 Flash

Unavailable in this round

GPT-5.6 Terra and Gemini 3.6 Flash in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
GPT-5.6 Terramax100.9
Gemini 3.6 Flashhigh97.2

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricGPT-5.6 TerraGemini 3.6 Flash
Intelligence
Overall indexpoints, 100 = reference group average, higher is better100.997.2
RankRank 31 of 95Rank 38 of 95
Price per 1M tokens
Inputwhat you send$2above 272,000 tokens: $4$0.75
Outputwhat the model writes$12above 272,000 tokens: $18$3.75
Cost per task (own tests)average of 2 original-protocol tasks both models passed (SVG short test not included)$0.05$0.051
Speed
Tokens per second77114
Technical
Context windowhow much text the model reads at once1.05 M tokens≈ 1,580 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffFeb 16, 2026March 2026
ReleasedJul 9, 2026Jul 21, 2026
AvailabilityActiveActive
Open weightsnono

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of GPT-5.6 TerraGPT-6.1 Terra

Overall index 106.5, rank 19$1 input and $5 output per 1M tokens

Gemini 3.6 Flash vs. GPT-6.1 Terra
Successor of Gemini 3.6 FlashGemini 3.7 Flash

Overall index 107.7, rank 17No API price in our data yet

GPT-5.6 Terra vs. Gemini 3.7 Flash
Cheaper than Gemini 3.6 FlashMuse Ember 1.0

Overall index 110.5, rank 14$0.10 input and $0.50 output per 1M tokens

View profile

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: GPT-5.6 TerraB: Gemini 3.6 Flash

Code MigrationOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 47.8%Gemini 3.6 Flash: 30.9%Vals AIAs of 10/29/2026
CorpFin v2Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 65.3%Gemini 3.6 Flash: 63.3%Vals AIAs of 08/12/2026
CyberBench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 72.1%Gemini 3.6 Flash: 45.4%Vals AIAs of 11/05/2026
EMBOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 66.2%Gemini 3.6 Flash: 65.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 54.4%Gemini 3.6 Flash: 56.3%Vals AIAs of 10/29/2026
Financial Coaching BenchOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 71.0%Gemini 3.6 Flash: 65.8%Vals AIAs of 11/13/2026
GDPval-AAOverall · higher is betterGPT-5.6 Terra: 1,387.3 eloGemini 3.6 Flash: 1,294.6 eloArtificial AnalysisAs of 11/07/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 90.9%Gemini 3.6 Flash: 93.4%Vals AIAs of 09/01/2026
IOIOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 87.6%Gemini 3.6 Flash: 35.1%Vals AIAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 41.3%Gemini 3.6 Flash: 25.0%Vals AIAs of 11/05/2026
Show 54 more benchmarks
LegalBenchOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 85.1%Gemini 3.6 Flash: 86.7%Vals AIAs of 10/13/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 85.9%Gemini 3.6 Flash: 88.1%Vals AIAs of 09/01/2026
LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,468Gemini 3.6 Flash: 1,483LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,266Gemini 3.6 Flash: 1,280LMArenaAs of 11/09/2026
MedCodeOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 43.4%Gemini 3.6 Flash: 53.2%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 82.9%Gemini 3.6 Flash: 79.7%Vals AIAs of 10/29/2026
MMLU ProOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 86.7%Gemini 3.6 Flash: 89.3%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 86.5%Gemini 3.6 Flash: 88.4%Vals AIAs of 09/01/2026
MMMU-ProOverall · higher is betterGPT-5.6 Terra: 79.1%Gemini 3.6 Flash: 83.2%Artificial AnalysisAs of 11/07/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 67.3%Gemini 3.6 Flash: 67.6%Vals AIAs of 09/01/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 0.5%Gemini 3.6 Flash: 0.0%Vals AIAs of 11/05/2026
Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 62.4%Gemini 3.6 Flash: 56.6%Vals AIAs of 10/12/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 95.4%Gemini 3.6 Flash: 79.6%Vals AIAs of 09/01/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 30%Gemini 3.6 Flash: 18%Vals AIAs of 11/05/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 76.2%Gemini 3.6 Flash: 74.9%Vals AIAs of 09/01/2026
Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 10.0%Gemini 3.6 Flash: 4.3%Vals AIAs of 11/05/2026
Vals Multimodal IndexOverall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 65.1%Gemini 3.6 Flash: 65.1%Vals AIAs of 08/11/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 74.6%Gemini 3.6 Flash: 64.0%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 40.4%Gemini 3.6 Flash: 19.3%Vals AIAs of 10/29/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 63.2%Gemini 3.6 Flash: 61.1%Vals AIAs of 08/12/2026
CyberBench v1.1Patch · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 87.5%Gemini 3.6 Flash: 85.7%Vals AIAs of 11/05/2026
EMBComps · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 62.2%Gemini 3.6 Flash: 70.0%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 49.7%Gemini 3.6 Flash: 53.6%Vals AIAs of 10/29/2026
Financial Coaching BenchElicitation · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 61.1%Gemini 3.6 Flash: 48.7%Vals AIAs of 11/13/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 89.9%Gemini 3.6 Flash: 92.4%Vals AIAs of 09/01/2026
IOIIOI 2024 · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 85.0%Gemini 3.6 Flash: 40.7%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 57.6%Gemini 3.6 Flash: 31.8%Vals AIAs of 11/05/2026
LegalBenchConclusion Tasks · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 90.3%Gemini 3.6 Flash: 91.1%Vals AIAs of 10/13/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 97.2%Gemini 3.6 Flash: 99.1%Vals AIAs of 09/01/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,466Gemini 3.6 Flash: 1,474LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,303Gemini 3.6 Flash: 1,330LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 93.0%Gemini 3.6 Flash: 94.7%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 74.3%Gemini 3.6 Flash: 76.8%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 15.0%Gemini 3.6 Flash: 2.5%Vals AIAs of 11/05/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 96.9%Gemini 3.6 Flash: 87.1%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 16.7%Gemini 3.6 Flash: 3.3%Vals AIAs of 11/05/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 65.8%Gemini 3.6 Flash: 63.5%Vals AIAs of 09/01/2026
Terminal-Bench-ScienceEarth Sciences · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 0.0%Gemini 3.6 Flash: 12.5%Vals AIAs of 11/05/2026
Vals Multimodal IndexCorpFin v2 · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 66.4%Gemini 3.6 Flash: 63.5%Vals AIAs of 08/11/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 70.0%Gemini 3.6 Flash: 65.7%Vals AIAs of 10/29/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 66.3%Gemini 3.6 Flash: 65.4%Vals AIAs of 08/12/2026
CyberBench v1.1PoC · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 56.7%Gemini 3.6 Flash: 5.0%Vals AIAs of 11/05/2026
EMBDataroom · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 82.2%Gemini 3.6 Flash: 73.0%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 42.8%Gemini 3.6 Flash: 44.6%Vals AIAs of 10/29/2026
Financial Coaching BenchLength-Controlled · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 70.9%Gemini 3.6 Flash: 65.8%Vals AIAs of 11/13/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 91.9%Gemini 3.6 Flash: 94.4%Vals AIAs of 09/01/2026
IOIIOI 2025 · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 77.8%Gemini 3.6 Flash: 40.8%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 88.8%Gemini 3.6 Flash: 83.5%Vals AIAs of 11/05/2026
LegalBenchInterpretation Tasks · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 83.2%Gemini 3.6 Flash: 83.9%Vals AIAs of 10/13/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 72.9%Gemini 3.6 Flash: 74.6%Vals AIAs of 09/01/2026
LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,516Gemini 3.6 Flash: 1,532LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 1,250Gemini 3.6 Flash: 1,253LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 90.9%Gemini 3.6 Flash: 92.8%Vals AIAs of 09/01/2026
MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identicalGPT-5.6 Terra: 60.3%Gemini 3.6 Flash: 58.4%Vals AIAs of 09/01/2026

More comparisons

Compare GPT-5.6 Terra and Gemini 3.6 Flash with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1GPT-6 Luna vs. GPT-5.6 Terra
  2. 2GPT-6.1 Sol vs. GPT-5.6 Terra
  3. 3Claude Sonnet 5.5 vs. GPT-5.6 Terra
  4. 4Claude Opus 5.5 vs. GPT-5.6 Terra
  5. 5GPT-5.6 Terra vs. DeepSeek-V4.1-Flash
  6. 6GPT-6 Astra vs. GPT-5.6 Terra
  7. 7GPT-6 Sol vs. GPT-5.6 Terra
  8. 8Claude Sonnet 5.5 vs. Gemini 3.6 Flash
  9. 9Gemini 3.8 Flash vs. Gemini 3.6 Flash
Show all 33 comparisons
  1. 10GPT-5.6 Terra vs. Grok 4.7
  2. 11Gemini 3.6 Flash vs. DeepSeek-V4.1-Flash
  3. 12Claude Opus 5 vs. GPT-5.6 Terra
  4. 13GPT-6 Luna vs. Gemini 3.6 Flash
  5. 14Gemini 3.6 Flash vs. Gemini 3.1 Pro Preview
  6. 15Claude Opus 5.5 vs. Gemini 3.6 Flash
  7. 16Claude Haiku 5.5 vs. Gemini 3.6 Flash
  8. 17GPT-5.6 Terra vs. DeepSeek-V4-Flash
  9. 18Claude Haiku 5.5 vs. GPT-5.6 Terra
  10. 19GPT-5.6 Terra vs. DeepSeek V4.1 Flash 1017
  11. 20Gemini 4 Carbon vs. Gemini 3.6 Flash
  12. 21Gemini 3.6 Flash vs. Qwen 3.8 27B
  13. 22GPT-5.6 Terra vs. Gemini 3.1 Pro Preview
  14. 23GPT-5.6 Terra vs. Gemini 3.7 Flash
  15. 24GPT-5.6 Terra vs. GPT-5.4
  16. 25Claude Sonnet 4.6 vs. GPT-5.6 Terra
  17. 26GPT-6.1 Sol vs. Gemini 3.6 Flash
  18. 27GPT-6.1 Terra vs. Gemini 3.6 Flash
  19. 28Gemini 3.6 Flash vs. DeepSeek V4.1 Flash 1017
  20. 29GPT-5.6 Terra vs. Mistral Large 3
  21. 30GPT-6 Sol vs. Gemini 3.6 Flash
  22. 31Claude Opus 4.6 vs. Gemini 3.6 Flash
  23. 32Gemini 4 Argon vs. Gemini 3.6 Flash
  24. 33GPT-5.6 Terra vs. Gemini 4 Argon