Gemini 4 Carbonvs.Gemini 4 Argon
What has improved?
In the overall index both are level: the gap is too small for a clear winner.
96
Gemini 4 Carbon
Rank 1 to 5
93
Gemini 4 Argon
Rank 2 to 7
100
Gemini 4 Carbon
fairly fast
82
Gemini 4 Argon
fairly slow
n/a
Gemini 4 Carbon
$4
Gemini 4 Argon
fairly expensive
Gemini 4 Carbon
- Subscription
Subscriptions in Germany: n/a
- Via API
n/a (no API price known).
Gemini 4 Argon
- Subscription
At Google DeepMind from €21.99 a month (Google AI Pro, with limited credits). Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 28 plans in Germany.
- Via API
$2 input, $10 output per 1M tokens.
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
Gemini 4 Carbon ahead: 2Gemini 4 Argon ahead: 0level: 4too little data: 3of 9 areas
AreaGemini 4 CarbonGemini 4 Argon0 to 100, higher is betterResult
Areas in the overall index
CodinglevelGemini 4 Carbon: 92Gemini 4 Argon: 90
ReasoninglevelGemini 4 Carbon: 96Gemini 4 Argon: 90
Mathematicsonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 90
KnowledgeGemini 4 Carbon aheadGemini 4 Carbon: above 99Gemini 4 Argon: 97
AgentsGemini 4 Carbon aheadGemini 4 Carbon: 88Gemini 4 Argon: 80
Generalonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 92
Specialist fields
FinancelevelGemini 4 Carbon: 94Gemini 4 Argon: 92
LegallevelGemini 4 Carbon: 94Gemini 4 Argon: 91
Healthonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 93
Show 3 more areas that do not count toward the overall index
AreaGemini 4 CarbonGemini 4 Argon0 to 100, higher is betterResult
Cybersecurityonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 97
Productivityonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 91
Educationonly Gemini 4 Argon has a scoreGemini 4 Carbon: not enough dataGemini 4 Argon: 90
See for yourself: same task, one attempt
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | Gemini 4 Carbon | Gemini 4 Argon |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 96 | 93 |
| Rank | Rank 1 to 5 of 95 | Rank 2 to 7 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | n/a | $2 |
| Outputwhat the model writes | n/a | $10 |
| Speed | ||
| Tokens per second | 100 | 82 |
| Technical | ||
| Context windowhow much text the model reads at once | 1 M tokens≈ 1,500 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | n/a | n/a |
| Released | n/a | Oct 13, 2026 |
| Availability | Limited access | Active |
| Open weights | no | no |
- Gemini 4 Carbon, Announced introductory pricing: $2 input and $10 output per 1M tokens. Cached input receives a 95% discount, giving $0.10 per 1M tokens. This announcement does not establish an already available public API. Source
- Gemini 4 Carbon, Announced pricing after the introductory period: Afterward, $4 input and $20 output per 1M tokens. Google has not specified when the introductory period ends. Source
- Gemini 4 Carbon, Artificial Analysis pricing assumptions: Artificial Analysis calculates test costs using $4 input, $20 output, and $0.20 cached input per 1M tokens. These are the evaluator’s pricing assumptions, not confirmation of a publicly available API tariff. Source
- Gemini 4 Argon, Standard pricing through November 30, 2026: Per 1 million tokens: $2.00 input, $10.00 output including thinking, and $0.10 cached input. Source
- Gemini 4 Argon, Standard pricing from December 1, 2026: Per 1 million tokens: $4.00 input, $20.00 output including thinking, and $0.20 cached input. Source
- Gemini 4 Argon, Caching: Implicit caching only; explicit caching is not supported. Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
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: Gemini 4 CarbonB: Gemini 4 Argon
AA-BriefcaseOverall · higher is betterGemini 4 Carbon: 1,609.49 eloGemini 4 Argon: 1,483.28 eloArtificial AnalysisAs of 10/29/2026
AA-OmniscienceOverall · higher is betterGemini 4 Carbon: 53.5 pointsGemini 4 Argon: 46.1 pointsArtificial AnalysisAs of 10/29/2026
AA-Omniscience AccuracyOverall · higher is betterGemini 4 Carbon: 58.3%Gemini 4 Argon: 48.3%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterGemini 4 Carbon: 11.4%Gemini 4 Argon: 4.3%Artificial AnalysisAs of 10/29/2026
Artificial Analysis Intelligence IndexOverall · higher is betterGemini 4 Carbon: 59.426 pointsGemini 4 Argon: 50.412 pointsArtificial AnalysisAs of 10/29/2026
AutomationBench-AAOverall · higher is betterGemini 4 Carbon: 77.8%Gemini 4 Argon: 77.5%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterGemini 4 Carbon: 36.0%Gemini 4 Argon: 27.1%Artificial AnalysisAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterGemini 4 Carbon: 63.0%Gemini 4 Argon: 52.5%Artificial AnalysisAs of 10/29/2026
FrontierCodeOverall · higher is betterGemini 4 Carbon: 40.6%Gemini 4 Argon: 25.7%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterGemini 4 Carbon: 48.5%Gemini 4 Argon: 43.5%Artificial AnalysisAs of 10/29/2026
Show 14 more benchmarks
GDP.pdfOverall · higher is betterGemini 4 Carbon: 28.4%Gemini 4 Argon: 21.8%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterGemini 4 Carbon: 1,733.07 eloGemini 4 Argon: 1,631.09 eloArtificial AnalysisAs of 10/29/2026
HLE-DiamondOverall · higher is betterGemini 4 Carbon: 69.1%Gemini 4 Argon: 56.7%Artificial AnalysisAs of 10/29/2026
Terminal-BenchOverall · higher is betterGemini 4 Carbon: 65.2%Gemini 4 Argon: 57.1%Artificial AnalysisAs of 10/29/2026
Terminal-Bench-ScienceOverall · higher is betterGemini 4 Carbon: 64.8%Gemini 4 Argon: 52.9%Artificial AnalysisAs of 10/29/2026
Vals IndexOverall · higher is betterTest setup not documented as identicalGemini 4 Carbon: 70.4%Gemini 4 Argon: 69.2%Vals AIAs of 10/27/2026
Vals IndexCode Migration v1.1 · higher is betterGemini 4 Carbon: 80.1%Gemini 4 Argon: 74.4%Vals AIAs of 10/27/2026
Vals IndexEMB v1.1 · higher is betterTest setup not documented as identicalGemini 4 Carbon: 76.5%Gemini 4 Argon: 74.8%Vals AIAs of 10/27/2026
Vals IndexFinance Agent v2.1 · higher is betterTest setup not documented as identicalGemini 4 Carbon: 67.2%Gemini 4 Argon: 67.7%Vals AIAs of 10/27/2026
Vals IndexHLAB-Vals-1.1 · higher is betterTest setup not documented as identicalGemini 4 Carbon: 17.5%Gemini 4 Argon: 27.1%Vals AIAs of 10/27/2026
Vals IndexLegal Research · higher is betterTest setup not documented as identicalGemini 4 Carbon: 55.8%Gemini 4 Argon: 54.8%Vals AIAs of 10/27/2026
Vals IndexTax Agent · higher is betterTest setup not documented as identicalGemini 4 Carbon: 48.9%Gemini 4 Argon: 44.6%Vals AIAs of 10/27/2026
Vals IndexTerminal-Bench 4.0 · higher is betterTest setup not documented as identicalGemini 4 Carbon: 63.1%Gemini 4 Argon: 57.6%Vals AIAs of 10/27/2026
Vals IndexVibe Code Bench v1.1 · higher is betterTest setup not documented as identicalGemini 4 Carbon: 89.1%Gemini 4 Argon: 91.9%Vals AIAs of 10/27/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare Gemini 4 Carbon and Gemini 4 Argon with other leading models.