DeepSeek V4 Pro 0423 vs Gemini 4 Carbon
Gemini 4 Carbon leads DeepSeek V4 Pro 0423 on coding, 86.6 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 3.8x less per output token ($2.60 vs $10.00 per million). Updated November 14, 2026; 45 benchmarks have a result for both.
DeepSeek V4 Pro 0423 or Gemini 4 Carbon: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5.
Pick DeepSeek V4 Pro 0423 for output tokens 3.8x cheaper ($2.60 vs $10.00 per million).
- Shared results
- 45
- DeepSeek V4 Pro 0423 only
- 44
- Gemini 4 Carbon only
- 28
- 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 38.7.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 60.0 against 12.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Pro 0423 has a GPQA Diamond result, 89.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0423 has a MMLU Pro result, 87.3%.
Directional only
Web design
Design Arena: websites
Gemini 4 Carbon
Gemini 4 Carbon leads, 1319 against 1227.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Carbon has a Vals Index result, 70.5%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 $0.0026, Gemini 4 Carbon $0.0070 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0423 has the number, $0.57.
Directional only
At a glance
- Coding index
- DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, Gemini 4 Carbon 86.6 from 4 benchmarks.
- Widest category
- Agentic work, 46.3 points apart on average over 3 shared benchmarks.
- Widest single gap
- FrontierMath, tier 4: DeepSeek V4 Pro 0423 2.4% against Gemini 4 Carbon 95.1%, 92.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $2.60 against Gemini 4 Carbon $10.00 per million output tokens, 3.8x apart.
- 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 | DeepSeek V4 Pro 0423 | Bars | Gemini 4 Carbon | Ties |
|---|---|---|---|---|
| Coding | 0 | 8 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 3 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 5 | ||
| Knowledge | 0 | 5 | ||
| Web design | 0 | 5 | ||
| General | 0 | 11 | ||
| All shared boards | 0 | 45 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 91.0% | Only Gemini 4 Carbon measured |
| LMArena WebDev | 1448 | 1768 | Gemini 4 Carbon |
| LiveCodeBench (Vals AI) | 87.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SWE-bench Verified (Vals AI) | 77.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 4 (Vals AI) | 11.1% | 63.1% | Gemini 4 Carbon |
| Vibe Code Bench (Vals AI) | 49.9% | 89.1% | Gemini 4 Carbon |
| Code migration (Vals AI) | 26.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SkillsBench (Vals AI) | 51.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | Not measured | 65.2% | Only Gemini 4 Carbon measured |
| FrontierCode 2.0 | Not measured | 40.6% | Only Gemini 4 Carbon measured |
| FrontierCode | 17.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierSWE | Not measured | 61.2% | Only Gemini 4 Carbon measured |
| WeirdML | 48.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ALE-Bench | 1006.1 | 2374.7 | Gemini 4 Carbon |
| LMArena Text: coding | 1469 | 1564 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1469 | 1552 | Gemini 4 Carbon |
| LMArena WebDev: React | 1441 | 1792 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1434 | 1770 | Gemini 4 Carbon |
| SWE Atlas: Codebase QnA | 27.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SWE Atlas: Test Writing | 27.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| GameBench 2 | 51.4 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CursorBench 4.0 | Not measured | 60.4% | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.6 | 60.0 | Gemini 4 Carbon |
| Epoch Capabilities Index | 150.2 | 169.8 | Gemini 4 Carbon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1000 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building full-stack apps | 948 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building mobile apps | Not measured | 1284 | Only Gemini 4 Carbon measured |
| Design Arena: agents building Godot games | 1059 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: spreadsheets | Not measured | 1224 | Only Gemini 4 Carbon measured |
| LiveBench research | Not measured | 92.5% | Only Gemini 4 Carbon measured |
| LiveBench browser | Not measured | 80.0% | Only Gemini 4 Carbon measured |
| LiveBench long agentic | Not measured | 72.7% | Only Gemini 4 Carbon measured |
| Finance Agent (Vals AI) | 44.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Tax Agent Bench (Vals AI) | 25.2% | 51.8% | Gemini 4 Carbon |
| Legal Research Bench (Vals AI) | 23.1% | 55.8% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 17.5% | Only Gemini 4 Carbon measured |
| Excel Modeling Benchmark (Vals AI) | 51.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| APEX-Agents | Not measured | 84.2% | Only Gemini 4 Carbon measured |
| Vending-Bench 2 | $3,285 | $16,484 | Gemini 4 Carbon |
| Toolathlon-Verified | 55.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench reasoning | Not measured | 90.6% | Only Gemini 4 Carbon measured |
| HLE-Diamond (Artificial Analysis run) | Not measured | 69.1% | Only Gemini 4 Carbon measured |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 69.0% | Only Gemini 4 Carbon measured |
| GPQA Diamond (Epoch AI run) | 90.9% | 96.5% | Gemini 4 Carbon |
| ARC-AGI | Not measured | 98.5% | Only Gemini 4 Carbon measured |
| ARC-AGI-2 | Not measured | 94.2% | Only Gemini 4 Carbon measured |
| SimpleBench | Not measured | 92.6% | Only Gemini 4 Carbon measured |
| Chess puzzles | 19.0% | 78.0% | Gemini 4 Carbon |
| Mystery game puzzles | 17.0% | 73.0% | Gemini 4 Carbon |
| EBR-bench | Not measured | 87.6% | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts | 1461 | 1551 | Gemini 4 Carbon |
| LMArena Text: expert | 1463 | 1582 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1466 | 1545 | Gemini 4 Carbon |
| Kagi LLM Benchmark | 53.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Humanity's Last Exam (Scale run) | 13.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| OTIS Mock AIME | 96.7% | 100.0% | Gemini 4 Carbon |
| FrontierMath, tiers 1 to 3 | 45.3% | 90.5% | Gemini 4 Carbon |
| FrontierMath, tier 4 | 2.4% | 95.1% | Gemini 4 Carbon |
| ProofBench | 16.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: math | 1442 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: mathematical work | 1455 | 1538 | Gemini 4 Carbon |
| MathArena | 24.5% | 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 index05
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LegalBench (Vals AI) | 80.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CaseLaw (Vals AI) | 59.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CorpFin (Vals AI) | 61.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| TaxEval (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| MedCode (Vals AI) | 40.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| AA-Omniscience | Not measured | 53.5 | Only Gemini 4 Carbon measured |
| SimpleQA Verified | 47.0% | 77.7% | Gemini 4 Carbon |
| LMArena Text: science | 1468 | 1535 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1465 | 1525 | Gemini 4 Carbon |
| LMArena Text: legal and government | 1464 | 1542 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1443 | 1520 | Gemini 4 Carbon |
| FACTS Benchmark Suite | Not measured | 78.4% | Only Gemini 4 Carbon measured |
| PRBench Legal | Not measured | 53.3% | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Design Arena: websites | 1227 | 1319 | Gemini 4 Carbon |
| Design Arena: UI components | 1211 | 1357 | Gemini 4 Carbon |
| Design Arena: game dev | 1221 | 1326 | Gemini 4 Carbon |
| Design Arena: data viz | 1200 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: 3D | 1232 | 1434 | Gemini 4 Carbon |
| Design Arena: all code categories | 1231 | 1348 | Gemini 4 Carbon |
| Design Arena: SVG | 1128 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: ASCII art | 1143 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench design | Not measured | 80.2% | Only Gemini 4 Carbon measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | DeepSeek V4 Pro 0423 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Vals Index | Not measured | 70.5% | Only Gemini 4 Carbon measured |
| LiveBench data analysis | Not measured | 86.5% | Only Gemini 4 Carbon measured |
| Public Benefits Bench (Vals AI) | 62.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| MedScribe (Vals AI) | 75.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Long context reasoning (AA-LCR) | Not measured | 79.3% | Only Gemini 4 Carbon measured |
| GDPval-AA | Not measured | 1733 | Only Gemini 4 Carbon measured |
| DTBench | 90.7% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMCA | 41.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Surface Evolver Bench | 40.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Furniture assembly | Not measured | 77.5% | Only Gemini 4 Carbon measured |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1538 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1446 | 1539 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1446 | 1533 | Gemini 4 Carbon |
| LMArena Text: English | 1459 | 1530 | Gemini 4 Carbon |
| LMArena Text: non-English | 1439 | 1534 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1481 | 1613 | Gemini 4 Carbon |
| LMArena Text: German | 1457 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Japanese | 1445 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Korean | 1407 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: French | 1472 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Spanish | 1456 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Russian | 1454 | 1560 | Gemini 4 Carbon |
| LMArena Text: Polish | 1459 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: multi-turn | 1467 | 1569 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1458 | 1549 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1447 | 1542 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1431 | 1527 | Gemini 4 Carbon |
| EQ-Bench 4 | 1156 | Not measured | Only DeepSeek V4 Pro 0423 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 | DeepSeek V4 Pro 0423 | 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
DeepSeek V4 Pro 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Pro 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Pro 0423 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 | DeepSeek V4 Pro 0423 | Google Gemini 4 Carbon |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | April 24, 2026 | November 10, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.30 | $2.00 |
| Output $/Mtok | $2.60 | $10.00 |
| Coding index | 38.7 | 86.6 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | $0.57 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than Gemini 4 Carbon for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 3.8x cheaper ($2.60 vs $10.00 per million).
Which is cheaper, DeepSeek V4 Pro 0423 or Gemini 4 Carbon?
DeepSeek V4 Pro 0423 costs $1.30 per million input tokens and $2.60 per million output tokens; Gemini 4 Carbon costs $2.00 and $10.00. Cost per solved task is known for DeepSeek V4 Pro 0423 only.
Which has the bigger context window, DeepSeek V4 Pro 0423 or Gemini 4 Carbon?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Pro 0423 vs Gemini 4 Carbon comparison based on?
45 benchmarks have a result for both models as of November 14, 2026. DeepSeek V4 Pro 0423'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.