Gemini 4 Carbon vs Step 5 Preview
Gemini 4 Carbon leads Step 5 Preview on coding, 86.6 to 57.4 on the Vibe Coding Index, and Step 5 Preview costs 3.7x less per output token ($2.70 vs $10.00 per million). Updated November 14, 2026; 45 benchmarks have a result for both.
Gemini 4 Carbon or Step 5 Preview: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 57.4 for Step 5 Preview.
Pick Step 5 Preview for output tokens 3.7x cheaper ($2.70 vs $10.00 per million) and work measured by Long context reasoning (AA-LCR), where it leads.
- Shared results
- 45
- Gemini 4 Carbon only
- 28
- Step 5 Preview only
- 30
- 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 57.4.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 60.0 against 28.5.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 4 Carbon has a Design Arena: websites result, 1319.
Directional only
General
Vals Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 70.5% against 54.8%.
Same board, both measured
Long documents
Listed context window
Gemini 4 Carbon
Gemini 4 Carbon takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 5 Preview
Gemini 4 Carbon $0.0070, Step 5 Preview $0.0024 per turn.
List prices
At a glance
- Coding index
- Gemini 4 Carbon 86.6 from 4 benchmarks, Step 5 Preview 57.4 from 4 benchmarks.
- Widest category
- Intelligence, 31.5 points apart on average over 1 shared benchmark.
- Widest single gap
- LiveBench browser: Gemini 4 Carbon 80.0% against Step 5 Preview 24.8%, 55.2 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Carbon $10.00 against Step 5 Preview $2.70 per million output tokens, 3.7x apart.
- Context window
- Gemini 4 Carbon takes 1.05M tokens, Step 5 Preview 1M.
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 Carbon | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 10 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 6 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 1 | 0 | ||
| General | 14 | 1 | ||
| All shared boards | 44 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index100
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | 91.0% | 67.6% | Gemini 4 Carbon |
| LMArena WebDev | 1768 | 1573 | Gemini 4 Carbon |
| Terminal-Bench 4 (Vals AI) | 63.1% | 31.8% | Gemini 4 Carbon |
| Vibe Code Bench (Vals AI) | 89.1% | 70.4% | Gemini 4 Carbon |
| Code migration (Vals AI) | Not measured | 39.0% | Only Step 5 Preview measured |
| IOI (Vals AI) | Not measured | 38.1% | Only Step 5 Preview measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Step 5 Preview measured |
| SciCode | Not measured | 58.9% | Only Step 5 Preview measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 65.2% | 33.3% | Gemini 4 Carbon |
| FrontierCode 2.0 | 40.6% | 12.0% | Gemini 4 Carbon |
| FrontierSWE | 61.2% | Not measured | Only Gemini 4 Carbon measured |
| ALE-Bench | 2374.7 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: coding | 1564 | 1482 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1552 | 1471 | Gemini 4 Carbon |
| LMArena WebDev: React | 1792 | 1589 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1770 | 1546 | Gemini 4 Carbon |
| LMArena WebDev: from an image | Not measured | 1551 | Only Step 5 Preview measured |
| GameBench 2 | Not measured | 52.6 | Only Step 5 Preview measured |
| CursorBench 4.0 | 60.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 60.0 | 28.5 | Gemini 4 Carbon |
| Epoch Capabilities Index | 169.8 | Not measured | Only Gemini 4 Carbon measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| Design Arena: agents building mobile apps | 1284 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: spreadsheets | 1224 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench research | 92.5% | 75.5% | Gemini 4 Carbon |
| LiveBench browser | 80.0% | 24.8% | Gemini 4 Carbon |
| LiveBench long agentic | 72.7% | 19.4% | Gemini 4 Carbon |
| SREBench (Vals AI) | Not measured | 0.4% | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | Not measured | 50.7% | Only Step 5 Preview measured |
| Tax Agent Bench (Vals AI) | 51.8% | 27.3% | Gemini 4 Carbon |
| Legal Research Bench (Vals AI) | 55.8% | 40.4% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | 12.9% | Gemini 4 Carbon |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.1% | Only Step 5 Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 67.4% | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Step 5 Preview measured |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| APEX-Agents | 84.2% | Not measured | Only Gemini 4 Carbon measured |
| Vending-Bench 2 | $16,484 | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench reasoning | 90.6% | 83.8% | Gemini 4 Carbon |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 46.5% | Only Step 5 Preview measured |
| HLE-Diamond (Artificial Analysis run) | 69.1% | 24.3% | Gemini 4 Carbon |
| CritPt v2, hard subset (Artificial Analysis run) | 69.0% | 32.5% | Gemini 4 Carbon |
| GPQA Diamond (Epoch AI run) | 96.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI | 98.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI-2 | 94.2% | Not measured | Only Gemini 4 Carbon measured |
| SimpleBench | 92.6% | Not measured | Only Gemini 4 Carbon measured |
| Chess puzzles | 78.0% | Not measured | Only Gemini 4 Carbon measured |
| Mystery game puzzles | 73.0% | Not measured | Only Gemini 4 Carbon measured |
| EBR-bench | 87.6% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts | 1551 | 1463 | Gemini 4 Carbon |
| LMArena Text: expert | 1582 | 1478 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1545 | 1463 | Gemini 4 Carbon |
| LMArena Vision: diagrams | Not measured | 1295 | Only Step 5 Preview measured |
| LMArena Vision: homework | Not measured | 1274 | Only Step 5 Preview measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tiers 1 to 3 | 90.5% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tier 4 | 95.1% | Not measured | Only Gemini 4 Carbon measured |
| ProofBench | Not measured | 42.0% | Only Step 5 Preview measured |
| LMArena Text: math | Not measured | 1462 | Only Step 5 Preview measured |
| LMArena Text: mathematical work | 1538 | 1465 | Gemini 4 Carbon |
| MathArena | 85.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| AA-Omniscience | 53.5 | 16.4 | Gemini 4 Carbon |
| SimpleQA Verified | 77.7% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: science | 1535 | 1462 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1525 | 1441 | Gemini 4 Carbon |
| LMArena Text: legal and government | 1542 | 1441 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1520 | 1444 | Gemini 4 Carbon |
| FACTS Benchmark Suite | 78.4% | Not measured | Only Gemini 4 Carbon measured |
| PRBench Legal | 53.3% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1319 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: UI components | 1357 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: game dev | 1326 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: 3D | 1434 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: all code categories | 1348 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench design | 80.2% | 70.8% | Gemini 4 Carbon |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index141
| Benchmark | Gemini 4 Carbon | Step 5 Preview | Leader |
|---|---|---|---|
| Vals Index | 70.5% | 54.8% | Gemini 4 Carbon |
| LiveBench data analysis | 86.5% | 63.5% | Gemini 4 Carbon |
| Public Benefits Bench (Vals AI) | Not measured | 58.1% | Only Step 5 Preview measured |
| Long context reasoning (AA-LCR) | 79.3% | 88.3% | Step 5 Preview |
| GDPval-AA | 1733 | 1591 | Gemini 4 Carbon |
| Furniture assembly | 77.5% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text | 1538 | 1443 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1539 | 1445 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1533 | 1415 | Gemini 4 Carbon |
| LMArena Vision | Not measured | 1263 | Only Step 5 Preview measured |
| LMArena Text: English | 1530 | 1455 | Gemini 4 Carbon |
| LMArena Text: non-English | 1534 | 1429 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1613 | 1495 | Gemini 4 Carbon |
| LMArena Text: German | Not measured | 1454 | Only Step 5 Preview measured |
| LMArena Text: Japanese | Not measured | 1397 | Only Step 5 Preview measured |
| LMArena Text: Korean | Not measured | 1404 | Only Step 5 Preview measured |
| LMArena Text: French | Not measured | 1446 | Only Step 5 Preview measured |
| LMArena Text: Spanish | Not measured | 1442 | Only Step 5 Preview measured |
| LMArena Text: Russian | 1560 | 1433 | Gemini 4 Carbon |
| LMArena Text: Polish | Not measured | 1405 | Only Step 5 Preview measured |
| LMArena Text: multi-turn | 1569 | 1440 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1549 | 1453 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1542 | 1429 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1527 | 1413 | Gemini 4 Carbon |
| LMArena Vision: English | Not measured | 1279 | Only Step 5 Preview measured |
| LMArena Vision: Chinese | Not measured | 1315 | Only Step 5 Preview measured |
| LMArena Vision: reading text | Not measured | 1278 | Only Step 5 Preview measured |
| LMArena Vision: creative writing | Not measured | 1251 | Only Step 5 Preview measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Carbon | Step 5 Preview | 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
Step 5 Preview costs less
Repository review
50K input + 3K output tokens
Step 5 Preview costs less
Agent loop
200K input + 10K output tokens
Step 5 Preview costs less
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 Carbon | StepFun Step 5 Preview |
|---|---|---|
| Maker | StepFun | |
| Weights | No public weights listed | Open weights |
| Released | November 10, 2026 | October 8, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $2.00 | $1.00 |
| Output $/Mtok | $10.00 | $2.70 |
| Coding index | 86.6 | 57.4 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Carbon better than Step 5 Preview for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 57.4 for Step 5 Preview. Pick Step 5 Preview for output tokens 3.7x cheaper ($2.70 vs $10.00 per million) and work measured by Long context reasoning (AA-LCR), where it leads.
Which is cheaper, Gemini 4 Carbon or Step 5 Preview?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemini 4 Carbon or Step 5 Preview?
Gemini 4 Carbon, with 1.05M tokens against 1M.
How many benchmarks is the Gemini 4 Carbon vs Step 5 Preview comparison based on?
45 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Carbon's coding index rests on 4 independent benchmarks and Step 5 Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.