DeepSeek V4 Pro 0813 vs Gemini 3.5 Flash
Updated October 21, 2026. 69 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick DeepSeek V4 Pro 0813 for coding: it scores 54.6 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash.
Pick Gemini 3.5 Flash when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
- Shared results
- 69
- DeepSeek V4 Pro 0813 only
- 9
- Gemini 3.5 Flash only
- 41
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 scores 54.6 against 42.8.
One benchmark behind each score
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads, 36.0 against 33.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0813 has a AA Agentic Index result, 41.3.
Directional only
Reasoning
GPQA Diamond
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 92.7% against 92.4%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.5 Flash
Gemini 3.5 Flash leads, 89.5% against 87.0%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 3.5 Flash has a Design Arena: websites result, 1268.
Directional only
General
Vals Index
No call
Only DeepSeek V4 Pro 0813 has a Vals Index result, 53.0%.
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 0813
DeepSeek V4 Pro 0813 $0.0016, Gemini 3.5 Flash $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 $0.10, Gemini 3.5 Flash $1.21.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Pro 0813 54.6 from 1 benchmark, Gemini 3.5 Flash 42.8 from 1 benchmark.
- Widest category
- Coding, 10.1 points apart on average over 16 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0813 82.3% against Gemini 3.5 Flash 48.7%, 33.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0813 $1.98 against Gemini 3.5 Flash $9.00 per million output tokens, 4.5x 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 0813 | Bars | Gemini 3.5 Flash | Ties |
|---|---|---|---|---|
| Coding | 10 | 5 | 1 tie | |
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 3 | ||
| Reasoning | 3 | 8 | ||
| Math | 3 | 2 | 1 tie | |
| Knowledge | 1 | 9 | ||
| General | 3 | 15 | ||
| All shared boards | 25 | 42 | 2 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index105
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1582 | 1499 | DeepSeek V4 Pro 0813 |
| AA Coding Index | 68.8 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveCodeBench (Vals AI) | 87.5% | 87.6% | Gemini 3.5 Flash |
| SWE-bench Verified (Vals AI) | 96.4% | 78.8% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 4 (Vals AI) | 14.1% | 6.1% | DeepSeek V4 Pro 0813 |
| Vibe Code Bench (Vals AI) | 82.3% | 48.7% | DeepSeek V4 Pro 0813 |
| Code migration (Vals AI) | 41.5% | 26.8% | DeepSeek V4 Pro 0813 |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | 51.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | 74.2% | Gemini 3.5 Flash |
| Vibe Code Bench 1-100 (Vals AI) | 17.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SkillsBench (Vals AI) | 53.8% | 52.7% | DeepSeek V4 Pro 0813 |
| CyberBench (Vals AI) | 72.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SciCode | 51.0% | 53.9% | Gemini 3.5 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 46.2% | Only Gemini 3.5 Flash measured |
| FrontierCode | 28.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| WeirdML | 66.2% | 62.6% | DeepSeek V4 Pro 0813 |
| ALE-Bench | 1403.2 | 911.0 | DeepSeek V4 Pro 0813 |
| LMArena Text: coding | 1469 | 1493 | Gemini 3.5 Flash |
| LMArena Text: software and IT | 1462 | 1494 | Gemini 3.5 Flash |
| LMArena WebDev: React | 1588 | 1495 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: HTML | 1566 | 1522 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: from an image | Not measured | 1504 | Only Gemini 3.5 Flash measured |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.0 | 33.6 | DeepSeek V4 Pro 0813 |
| Epoch Capabilities Index | 155.6 | 154.9 | DeepSeek V4 Pro 0813 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| AA Agentic Index | 41.3 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Design Arena: agents building web apps | Not measured | 1202 | Only Gemini 3.5 Flash measured |
| Design Arena: agents building full-stack apps | Not measured | 1197 | Only Gemini 3.5 Flash measured |
| Design Arena: agents building mobile apps | Not measured | 1175 | Only Gemini 3.5 Flash measured |
| Design Arena: agents building Android apps | Not measured | 1190 | Only Gemini 3.5 Flash measured |
| Design Arena: agents building Godot games | Not measured | 1098 | Only Gemini 3.5 Flash measured |
| Design Arena: agents building games | Not measured | 1180 | Only Gemini 3.5 Flash measured |
| Design Arena: HTML slides | Not measured | 1142 | Only Gemini 3.5 Flash measured |
| Design Arena: PowerPoint slides | Not measured | 1178 | Only Gemini 3.5 Flash measured |
| SREBench (Vals AI) | 1.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Finance Agent (Vals AI) | 50.4% | 57.9% | Gemini 3.5 Flash |
| Tax Agent Bench (Vals AI) | 26.8% | 21.6% | DeepSeek V4 Pro 0813 |
| Legal Research Bench (Vals AI) | 40.9% | 30.8% | DeepSeek V4 Pro 0813 |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Excel Modeling Benchmark (Vals AI) | 52.8% | 63.5% | Gemini 3.5 Flash |
| Terminal-Bench-Science (Vals AI) | 4.3% | 5.7% | Gemini 3.5 Flash |
| τ²-Bench Telecom | Not measured | 95.6% | Only Gemini 3.5 Flash measured |
| APEX-Agents | 47.3% | 27.5% | DeepSeek V4 Pro 0813 |
| Vending-Bench 2 | Not measured | $5,396 | Only Gemini 3.5 Flash measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index38
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | 92.7% | Gemini 3.5 Flash |
| MMMU Pro (Vals AI) | Not measured | 88.3% | Only Gemini 3.5 Flash measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | 92.2% | DeepSeek V4 Pro 0813 |
| Humanity's Last Exam (Artificial Analysis run) | 41.0% | 42.7% | Gemini 3.5 Flash |
| GPQA Diamond (Epoch AI run) | 91.7% | 92.8% | Gemini 3.5 Flash |
| ARC-AGI | 90.5% | 92.5% | Gemini 3.5 Flash |
| ARC-AGI-2 | 61.3% | 72.1% | Gemini 3.5 Flash |
| SimpleBench | Not measured | 76.7% | Only Gemini 3.5 Flash measured |
| Chess puzzles | 46.0% | 45.0% | DeepSeek V4 Pro 0813 |
| Mystery game puzzles | 43.0% | 32.0% | DeepSeek V4 Pro 0813 |
| EBR-bench | Not measured | 4.8% | Only Gemini 3.5 Flash measured |
| LMArena Text: hard prompts | 1458 | 1488 | Gemini 3.5 Flash |
| LMArena Text: expert | 1459 | 1495 | Gemini 3.5 Flash |
| LMArena Text: hard prompts in English | 1463 | 1483 | Gemini 3.5 Flash |
| LMArena Vision: diagrams | Not measured | 1323 | Only Gemini 3.5 Flash measured |
| LMArena Vision: homework | Not measured | 1330 | Only Gemini 3.5 Flash measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.6% | 95.6% | DeepSeek V4 Pro 0813 |
| FrontierMath, tiers 1 to 3 | 64.6% | 62.8% | DeepSeek V4 Pro 0813 |
| FrontierMath, tier 4 | 26.8% | 26.8% | Tie |
| ProofBench | 50.0% | 31.0% | DeepSeek V4 Pro 0813 |
| LMArena Text: math | 1441 | 1504 | Gemini 3.5 Flash |
| LMArena Text: mathematical work | 1443 | 1495 | Gemini 3.5 Flash |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 87.0% | 89.5% | Gemini 3.5 Flash |
| LegalBench (Vals AI) | 82.4% | 83.6% | Gemini 3.5 Flash |
| CorpFin (Vals AI) | 65.4% | 64.7% | DeepSeek V4 Pro 0813 |
| TaxEval (Vals AI) | 73.1% | 74.4% | Gemini 3.5 Flash |
| MortgageTax (Vals AI) | Not measured | 68.1% | Only Gemini 3.5 Flash measured |
| MedCode (Vals AI) | 42.5% | 55.8% | Gemini 3.5 Flash |
| SimpleQA Verified | 52.9% | 66.2% | Gemini 3.5 Flash |
| LMArena Text: science | 1457 | 1495 | Gemini 3.5 Flash |
| LMArena Text: medicine and healthcare | 1446 | 1483 | Gemini 3.5 Flash |
| LMArena Text: legal and government | 1459 | 1488 | Gemini 3.5 Flash |
| LMArena Text: business and finance | 1442 | 1467 | Gemini 3.5 Flash |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1268 | Only Gemini 3.5 Flash measured |
| Design Arena: UI components | Not measured | 1272 | Only Gemini 3.5 Flash measured |
| Design Arena: game dev | Not measured | 1263 | Only Gemini 3.5 Flash measured |
| Design Arena: data viz | Not measured | 1236 | Only Gemini 3.5 Flash measured |
| Design Arena: 3D | Not measured | 1244 | Only Gemini 3.5 Flash measured |
| Design Arena: all code categories | Not measured | 1266 | Only Gemini 3.5 Flash measured |
| Design Arena: SVG | Not measured | 1254 | Only Gemini 3.5 Flash measured |
| Design Arena: ASCII art | Not measured | 1253 | Only Gemini 3.5 Flash measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index315
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | Leader |
|---|---|---|---|
| Vals Index | 53.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Public Benefits Bench (Vals AI) | Not measured | 59.5% | Only Gemini 3.5 Flash measured |
| SAGE (Vals AI) | Not measured | 49.9% | Only Gemini 3.5 Flash measured |
| MedScribe (Vals AI) | 80.2% | 76.6% | DeepSeek V4 Pro 0813 |
| Vals Multimodal Index | Not measured | 62.9% | Only Gemini 3.5 Flash measured |
| IFBench | Not measured | 76.3% | Only Gemini 3.5 Flash measured |
| Long context reasoning (AA-LCR) | 80.3% | 74.3% | DeepSeek V4 Pro 0813 |
| DTBench | 93.9% | 94.7% | Gemini 3.5 Flash |
| LMCA | 45.5% | 47.1% | Gemini 3.5 Flash |
| Surface Evolver Bench | Not measured | 58.1% | Only Gemini 3.5 Flash measured |
| LMArena Text | 1446 | 1482 | Gemini 3.5 Flash |
| LMArena Text: instruction following | 1448 | 1467 | Gemini 3.5 Flash |
| LMArena Text: creative writing | 1439 | 1470 | Gemini 3.5 Flash |
| LMArena Vision | Not measured | 1308 | Only Gemini 3.5 Flash measured |
| LMArena Text: English | 1457 | 1481 | Gemini 3.5 Flash |
| LMArena Text: non-English | 1431 | 1475 | Gemini 3.5 Flash |
| LMArena Text: Chinese | 1481 | 1527 | Gemini 3.5 Flash |
| LMArena Text: German | Not measured | 1494 | Only Gemini 3.5 Flash measured |
| LMArena Text: Japanese | Not measured | 1486 | Only Gemini 3.5 Flash measured |
| LMArena Text: Korean | 1449 | 1448 | DeepSeek V4 Pro 0813 |
| LMArena Text: French | 1446 | 1490 | Gemini 3.5 Flash |
| LMArena Text: Spanish | 1435 | 1480 | Gemini 3.5 Flash |
| LMArena Text: Russian | 1448 | 1493 | Gemini 3.5 Flash |
| LMArena Text: Polish | Not measured | 1516 | Only Gemini 3.5 Flash measured |
| LMArena Text: multi-turn | 1454 | 1481 | Gemini 3.5 Flash |
| LMArena Text: longer queries | 1458 | 1483 | Gemini 3.5 Flash |
| LMArena Text: writing and language | 1443 | 1478 | Gemini 3.5 Flash |
| LMArena Text: entertainment and media | 1424 | 1459 | Gemini 3.5 Flash |
| LMArena Vision: English | Not measured | 1305 | Only Gemini 3.5 Flash measured |
| LMArena Vision: Chinese | Not measured | 1377 | Only Gemini 3.5 Flash measured |
| LMArena Vision: reading text | Not measured | 1317 | Only Gemini 3.5 Flash measured |
| LMArena Vision: humor | Not measured | 1321 | Only Gemini 3.5 Flash measured |
| LMArena Vision: creative writing | Not measured | 1301 | Only Gemini 3.5 Flash measured |
| LMArena Document | Not measured | 1463 | Only Gemini 3.5 Flash measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | Gemini 3.5 Flash | 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 0813 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Pro 0813 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Pro 0813 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 0813 | Google Gemini 3.5 Flash |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | August 12, 2026 | May 19, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.66 | $1.50 |
| Output $/Mtok | $1.98 | $9.00 |
| Coding index | 54.6 | 42.8 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.10 | $1.21 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0813 better than Gemini 3.5 Flash for coding?
Pick DeepSeek V4 Pro 0813 for coding: it scores 54.6 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash. Pick Gemini 3.5 Flash when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Pro 0813 or Gemini 3.5 Flash?
DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and Gemini 3.5 Flash $1.21.
Which has the bigger context window, DeepSeek V4 Pro 0813 or Gemini 3.5 Flash?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Pro 0813 vs Gemini 3.5 Flash comparison based on?
69 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Gemini 3.5 Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.