Gemini 4 Argon vs Gemini 4 Carbon
Gemini 4 Carbon leads Gemini 4 Argon on coding, 86.6 to 80.3 on the Vibe Coding Index, at about the same output price ($10.00 vs $10.00 per million). Updated November 14, 2026; 72 benchmarks have a result for both.
vs boards won of 72 shared, 2 tied
Gemini 4 Argon or Gemini 4 Carbon: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 80.3 for Gemini 4 Argon, though on 4 benchmarks against 5.
Pick Gemini 4 Argon for work measured by Vibe Code Bench (Vals AI) or LiveBench browser, where it leads.
Model AGemini 4 ArgonGoogle80.3/1005 independent benchmarksNo cost per solved taskModel BGemini 4 CarbonGoogle86.6/1004 independent benchmarksNo cost per solved task
- Shared results
- 72
- Gemini 4 Argon only
- 52
- Gemini 4 Carbon only
- 1
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Gemini 4 Carbon
Gemini 4 Carbon scores 86.6 against 80.3.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 60.0 against 50.4.
Same board, both measured
Web design
Design Arena: websites
Gemini 4 Carbon
Gemini 4 Carbon leads, 1319 against 1316.
Same board, both measured
General
Vals Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 70.5% against 69.4%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
No call
Gemini 4 Argon $0.0070, Gemini 4 Carbon $0.0070 per turn.
List prices
At a glance
- Coding index
- Gemini 4 Argon 80.3 from 5 benchmarks, Gemini 4 Carbon 86.6 from 4 benchmarks.
- Widest category
- Math, 9.4 points apart on average over 5 shared benchmarks.
- Widest single gap
- MathArena: Gemini 4 Argon 62.1% against Gemini 4 Carbon 85.4%, 23.3 points apart on a 0 to 100 scale.
- Output price
- Both cost $10.00 per million output tokens.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 4 Argon | Bars | Gemini 4 Carbon | Ties |
|---|---|---|---|---|
| Coding | 1 | 12 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 7 | ||
| Reasoning | 1 | 11 | 1 tie | |
| Math | 1 | 3 | 1 tie | |
| Knowledge | 2 | 6 | ||
| Web design | 1 | 5 | ||
| General | 2 | 14 | ||
| All shared boards | 10 | 60 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| LiveBench coding | 85.7% | 91.0% | Gemini 4 Carbon |
| LMArena WebDev | 1681 | 1768 | Gemini 4 Carbon |
| Terminal-Bench 4 (Vals AI) | 57.6% | 63.1% | Gemini 4 Carbon |
| Vibe Code Bench (Vals AI) | 91.9% | 89.1% | Gemini 4 Argon |
| Code migration (Vals AI) | 68.2% | Not measured | Only Gemini 4 Argon measured |
| ProgramBench (Vals AI) | 2.5% | Not measured | Only Gemini 4 Argon measured |
| IOI (Vals AI) | 100.0% | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench 2.1 (Vals AI) | 57.7% | Not measured | Only Gemini 4 Argon measured |
| SWE-bench Multimodal (Vals AI) | 56.0% | Not measured | Only Gemini 4 Argon measured |
| Vibe Code Bench 1-100 (Vals AI) | 21.2% | Not measured | Only Gemini 4 Argon measured |
| CyberBench (Vals AI) | 77.9% | Not measured | Only Gemini 4 Argon measured |
| SciCode | 61.8% | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 57.1% | 65.2% | Gemini 4 Carbon |
| FrontierCode 2.0 | 25.7% | 40.6% | Gemini 4 Carbon |
| FrontierCode | 47.5% | Not measured | Only Gemini 4 Argon measured |
| FrontierSWE | 55.0% | 61.2% | Gemini 4 Carbon |
| MirrorCode | 58.9% | Not measured | Only Gemini 4 Argon measured |
| ALE-Bench | 2100.1 | 2374.7 | Gemini 4 Carbon |
| LMArena Text: coding | 1540 | 1564 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1542 | 1552 | Gemini 4 Carbon |
| LMArena WebDev: React | 1702 | 1792 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1657 | 1770 | Gemini 4 Carbon |
| SciCode | 12.3% | Not measured | Only Gemini 4 Argon measured |
| SWE-Bench Pro V2 | 99.2% | Not measured | Only Gemini 4 Argon measured |
| GameBench 2 | 89.2 | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench 4.0 | 54.9% | Not measured | Only Gemini 4 Argon measured |
| CursorBench 4.0 | 52.9% | 60.4% | Gemini 4 Carbon |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| AA Intelligence Index | 50.4 | 60.0 | Gemini 4 Carbon |
| Epoch Capabilities Index | 166.5 | 169.8 | Gemini 4 Carbon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index27
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1284 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: agents building mobile apps | Not measured | 1284 | Only Gemini 4 Carbon measured |
| Design Arena: agents building games | 1264 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: spreadsheets | 1159 | 1224 | Gemini 4 Carbon |
| LiveBench research | 86.8% | 92.5% | Gemini 4 Carbon |
| LiveBench browser | 82.8% | 80.0% | Gemini 4 Argon |
| LiveBench long agentic | 58.5% | 72.7% | Gemini 4 Carbon |
| SREBench (Vals AI) | 44.3% | Not measured | Only Gemini 4 Argon measured |
| Finance Agent (Vals AI) | 65.4% | Not measured | Only Gemini 4 Argon measured |
| Tax Agent Bench (Vals AI) | 49.2% | 51.8% | Gemini 4 Carbon |
| Legal Research Bench (Vals AI) | 54.8% | 55.8% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | 27.1% | 17.5% | Gemini 4 Argon |
| Excel Modeling Benchmark (Vals AI) | 75.2% | Not measured | Only Gemini 4 Argon measured |
| BioMysteryBench (Vals AI) | 76.3% | Not measured | Only Gemini 4 Argon measured |
| Terminal-Bench-Science (Vals AI) | 44.3% | Not measured | Only Gemini 4 Argon measured |
| Vals Science Index | 55.4% | Not measured | Only Gemini 4 Argon measured |
| Time Horizon Index (Vals AI) | 52.5% | Not measured | Only Gemini 4 Argon measured |
| CUA-bench (Vals AI) | 4.8% | Not measured | Only Gemini 4 Argon measured |
| Robo-bench (Vals AI) | 0.8% | Not measured | Only Gemini 4 Argon measured |
| APEX-Agents | 82.4% | 84.2% | Gemini 4 Carbon |
| Remote Labor Index | 17.1% | Not measured | Only Gemini 4 Argon measured |
| PostTrainBench | 40.4% | Not measured | Only Gemini 4 Argon measured |
| Vending-Bench 2 | $13,718 | $16,484 | Gemini 4 Carbon |
| MCP Atlas | 90.7% | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index111
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| LiveBench reasoning | 95.1% | 90.6% | Gemini 4 Argon |
| MysteryMechanism (Vals AI) | 45.5% | Not measured | Only Gemini 4 Argon measured |
| Humanity's Last Exam (Artificial Analysis run) | 57.1% | Not measured | Only Gemini 4 Argon measured |
| HLE-Diamond (Artificial Analysis run) | 56.7% | 69.1% | Gemini 4 Carbon |
| CritPt v2, hard subset (Artificial Analysis run) | 53.5% | 69.0% | Gemini 4 Carbon |
| GPQA Diamond (Epoch AI run) | 96.4% | 96.5% | Gemini 4 Carbon |
| ARC-AGI | 98.5% | 98.5% | Tie |
| ARC-AGI-2 | 91.3% | 94.2% | Gemini 4 Carbon |
| SimpleBench | 91.7% | 92.6% | Gemini 4 Carbon |
| Chess puzzles | 59.0% | 78.0% | Gemini 4 Carbon |
| Mystery game puzzles | 64.0% | 73.0% | Gemini 4 Carbon |
| EBR-bench | 64.8% | 87.6% | Gemini 4 Carbon |
| LMArena Text: hard prompts | 1542 | 1551 | Gemini 4 Carbon |
| LMArena Text: expert | 1555 | 1582 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1540 | 1545 | Gemini 4 Carbon |
| Humanity's Last Exam (Scale run) | 53.2% | Not measured | Only Gemini 4 Argon measured |
| GoBench | 2352 | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 100.0% | Tie |
| FrontierMath, tiers 1 to 3 | 86.0% | 90.5% | Gemini 4 Carbon |
| FrontierMath, tier 4 | 78.0% | 95.1% | Gemini 4 Carbon |
| ProofBench | 99.0% | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: math | 1544 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: mathematical work | 1551 | 1538 | Gemini 4 Argon |
| MathArena | 62.1% | 85.4% | Gemini 4 Carbon |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index26
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 88.3% | Not measured | Only Gemini 4 Argon measured |
| MedCode (Vals AI) | 58.8% | Not measured | Only Gemini 4 Argon measured |
| AA-Omniscience | 46.1 | 53.5 | Gemini 4 Carbon |
| SimpleQA Verified | 76.0% | 77.7% | Gemini 4 Carbon |
| LMArena Text: science | 1546 | 1535 | Gemini 4 Argon |
| LMArena Text: medicine and healthcare | 1527 | 1525 | Gemini 4 Argon |
| LMArena Text: legal and government | 1541 | 1542 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1519 | 1520 | Gemini 4 Carbon |
| FACTS Benchmark Suite | 72.4% | 78.4% | Gemini 4 Carbon |
| PRBench Finance | 49.9% | Not measured | Only Gemini 4 Argon measured |
| PRBench Legal | 49.4% | 53.3% | Gemini 4 Carbon |
| Neither model has a result on the other 10 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Design Arena: websites | 1316 | 1319 | Gemini 4 Carbon |
| Design Arena: UI components | 1331 | 1357 | Gemini 4 Carbon |
| Design Arena: game dev | 1361 | 1326 | Gemini 4 Argon |
| Design Arena: data viz | 1327 | Not measured | Only Gemini 4 Argon measured |
| Design Arena: 3D | 1353 | 1434 | Gemini 4 Carbon |
| Design Arena: all code categories | 1326 | 1348 | Gemini 4 Carbon |
| Design Arena: SVG | 1338 | Not measured | Only Gemini 4 Argon measured |
| LiveBench design | 69.2% | 80.2% | Gemini 4 Carbon |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index214
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Vals Index | 69.4% | 70.5% | Gemini 4 Carbon |
| LiveBench data analysis | 85.2% | 86.5% | Gemini 4 Carbon |
| Public Benefits Bench (Vals AI) | 69.8% | Not measured | Only Gemini 4 Argon measured |
| SAGE (Vals AI) | 89.5% | Not measured | Only Gemini 4 Argon measured |
| MedScribe (Vals AI) | 87.4% | Not measured | Only Gemini 4 Argon measured |
| Long context reasoning (AA-LCR) | 79.7% | 79.3% | Gemini 4 Argon |
| GDPval-AA | 1634 | 1733 | Gemini 4 Carbon |
| DTBench | 97.6% | Not measured | Only Gemini 4 Argon measured |
| LMCA | 63.7% | Not measured | Only Gemini 4 Argon measured |
| Furniture assembly | 72.5% | 77.5% | Gemini 4 Carbon |
| LMArena Text | 1529 | 1538 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1536 | 1539 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1533 | 1533 | Gemini 4 Argon |
| LMArena Text: English | 1529 | 1530 | Gemini 4 Carbon |
| LMArena Text: non-English | 1523 | 1534 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1605 | 1613 | Gemini 4 Carbon |
| LMArena Text: German | 1582 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Japanese | 1532 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Korean | 1501 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: French | 1553 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Spanish | 1508 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: Russian | 1539 | 1560 | Gemini 4 Carbon |
| LMArena Text: Polish | 1537 | Not measured | Only Gemini 4 Argon measured |
| LMArena Text: multi-turn | 1548 | 1569 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1547 | 1549 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1532 | 1542 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1522 | 1527 | Gemini 4 Carbon |
| MultiChallenge | 78.7% | Not measured | Only Gemini 4 Argon measured |
| EQ-Bench 4 | 1236 | Not measured | Only Gemini 4 Argon measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Argon | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 4 Argon$0.0070Fits in one request
Gemini 4 Carbon$0.0070Fits in one request
Same cost
Repository review
50K input + 3K output tokens
Gemini 4 Argon$0.130Fits in one request
Gemini 4 Carbon$0.130Fits in one request
Same cost
Agent loop
200K input + 10K output tokens
Gemini 4 Argon$0.500Fits in one request
Gemini 4 Carbon$0.500Fits in one request
Same cost
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 4 Argon | Google Gemini 4 Carbon |
|---|---|---|
| Maker | ||
| Weights | No public weights listed | No public weights listed |
| Released | October 13, 2026 | November 10, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $2.00 |
| Output $/Mtok | $10.00 | $10.00 |
| Coding index | 80.3 | 86.6 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Argon better than Gemini 4 Carbon for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 80.3 for Gemini 4 Argon, though on 4 benchmarks against 5. Pick Gemini 4 Argon for work measured by Vibe Code Bench (Vals AI) or LiveBench browser, where it leads.
Which is cheaper, Gemini 4 Argon or Gemini 4 Carbon?
Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; Gemini 4 Carbon costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemini 4 Argon or Gemini 4 Carbon?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 4 Argon vs Gemini 4 Carbon comparison based on?
72 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Argon's coding index rests on 5 independent benchmarks and Gemini 4 Carbon's on 4. Where only one model has a result, the page says so instead of naming a winner.