DeepSeek V3.2 vs Gemini 3.1 Pro Preview
Updated October 21, 2026. 67 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 67 shared
Decision reading
Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview.
Pick Gemini 3.1 Pro Preview when the context window is larger, 1.05M against 164K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
Model ADeepSeek V3.2DeepSeek54.4/1002 independent benchmarks$0.99 per solved taskModel BGemini 3.1 Pro PreviewGoogle35.3/1001 independent benchmark$0.99 per solved task
- Shared results
- 67
- DeepSeek V3.2 only
- 8
- Gemini 3.1 Pro Preview only
- 64
- Like-for-like categories
- 8 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 V3.2
DeepSeek V3.2 scores 54.4 against 35.3.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 21.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 80.3%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 84.6%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 84.9%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1234 against 1175.
Same board, both measured
Long documents
Listed context window
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0005, Gemini 3.1 Pro Preview $0.0080 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
DeepSeek V3.2 $0.99, Gemini 3.1 Pro Preview $0.99.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 54.4 from 2 benchmarks, Gemini 3.1 Pro Preview 35.3 from 1 benchmark.
- Widest category
- Reasoning, 23.0 points apart on average over 8 shared benchmarks.
- Widest single gap
- ARC-AGI-2: DeepSeek V3.2 4.0% against Gemini 3.1 Pro Preview 77.1%, 73.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.42 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 28.6x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Gemini 3.1 Pro Preview 1.05M.
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 V3.2 | Bars | Gemini 3.1 Pro Preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 11 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 2 | ||
| Reasoning | 0 | 8 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 10 | ||
| Web design | 0 | 8 | ||
| General | 0 | 23 | ||
| All shared boards | 1 | 66 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index011
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | 1447 | Gemini 3.1 Pro Preview |
| AA Coding Index | 44.2 | 68.8 | Gemini 3.1 Pro Preview |
| LiveCodeBench (Vals AI) | 80.7% | 88.5% | Gemini 3.1 Pro Preview |
| SWE-bench Verified (Vals AI) | 67.6% | 78.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench 4 (Vals AI) | Not measured | 2.5% | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench (Vals AI) | 5.1% | 32.0% | Gemini 3.1 Pro Preview |
| Code migration (Vals AI) | Not measured | 17.3% | Only Gemini 3.1 Pro Preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Gemini 3.1 Pro Preview measured |
| IOI (Vals AI) | Not measured | 51.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 70.8% | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 6.7% | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 58.7% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | 53.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 39.6% | 80.2% | Gemini 3.1 Pro Preview |
| GSO-Bench | Not measured | 22.6% | Only Gemini 3.1 Pro Preview measured |
| WeirdML | Not measured | 72.1% | Only Gemini 3.1 Pro Preview measured |
| MirrorCode | Not measured | 8.9% | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | Not measured | 1160.6 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: coding | 1453 | 1484 | Gemini 3.1 Pro Preview |
| LMArena Text: software and IT | 1449 | 1487 | Gemini 3.1 Pro Preview |
| LMArena WebDev: React | 1350 | 1438 | Gemini 3.1 Pro Preview |
| LMArena WebDev: HTML | 1371 | 1490 | Gemini 3.1 Pro Preview |
| LMArena WebDev: from an image | Not measured | 1481 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 12 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 29.7 | Gemini 3.1 Pro Preview |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 8.2 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building web apps | Not measured | 1125 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building full-stack apps | Not measured | 1068 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building mobile apps | Not measured | 1094 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Android apps | Not measured | 1055 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Godot games | Not measured | 1236 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building games | Not measured | 1114 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: HTML slides | Not measured | 1153 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: PowerPoint slides | Not measured | 1064 | Only Gemini 3.1 Pro Preview measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only Gemini 3.1 Pro Preview measured |
| Finance Agent (Vals AI) | Not measured | 43.0% | Only Gemini 3.1 Pro Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 9.3% | Only Gemini 3.1 Pro Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 20.7% | Only Gemini 3.1 Pro Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 52.6% | Only Gemini 3.1 Pro Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 60.0% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Gemini 3.1 Pro Preview measured |
| Vals Science Index | Not measured | 27.4% | Only Gemini 3.1 Pro Preview measured |
| τ²-Bench Telecom | 90.6% | 95.6% | Gemini 3.1 Pro Preview |
| APEX-Agents | 21.3% | 35.1% | Gemini 3.1 Pro Preview |
| METR time horizons | Not measured | 77.0% | Only Gemini 3.1 Pro Preview measured |
| BALROG | Not measured | 57.0% | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | Not measured | 47.8% | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | Not measured | 22.0% | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | $1,034 | $911 | DeepSeek V3.2 |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 95.5% | Gemini 3.1 Pro Preview |
| MysteryMechanism (Vals AI) | Not measured | 20.7% | Only Gemini 3.1 Pro Preview measured |
| MMMU Pro (Vals AI) | Not measured | 88.2% | Only Gemini 3.1 Pro Preview measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 94.1% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 47.0% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | Not measured | 94.4% | Only Gemini 3.1 Pro Preview measured |
| ARC-AGI | 57.0% | 98.0% | Gemini 3.1 Pro Preview |
| ARC-AGI-2 | 4.0% | 77.1% | Gemini 3.1 Pro Preview |
| SimpleBench | Not measured | 79.6% | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | Not measured | 51.0% | Only Gemini 3.1 Pro Preview measured |
| Mystery game puzzles | Not measured | 34.0% | Only Gemini 3.1 Pro Preview measured |
| EBR-bench | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | 1434 | 1485 | Gemini 3.1 Pro Preview |
| LMArena Text: expert | 1436 | 1483 | Gemini 3.1 Pro Preview |
| LMArena Text: hard prompts in English | 1446 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Vision: diagrams | Not measured | 1311 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: homework | Not measured | 1316 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AIME | 84.6% | 98.1% | Gemini 3.1 Pro Preview |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| OTIS Mock AIME | Not measured | 95.6% | Only Gemini 3.1 Pro Preview measured |
| FrontierMath, tiers 1 to 3 | Not measured | 59.6% | Only Gemini 3.1 Pro Preview measured |
| FrontierMath, tier 4 | Not measured | 26.8% | Only Gemini 3.1 Pro Preview measured |
| ProofBench | Not measured | 26.0% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: math | 1435 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: mathematical work | 1440 | 1478 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 91.0% | Gemini 3.1 Pro Preview |
| LegalBench (Vals AI) | 76.1% | 87.4% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | 55.4% | 64.8% | Gemini 3.1 Pro Preview |
| CorpFin (Vals AI) | 51.0% | 64.5% | Gemini 3.1 Pro Preview |
| TaxEval (Vals AI) | 68.2% | 72.9% | Gemini 3.1 Pro Preview |
| MortgageTax (Vals AI) | Not measured | 69.4% | Only Gemini 3.1 Pro Preview measured |
| MedQA (Vals AI) | 93.9% | 96.4% | Gemini 3.1 Pro Preview |
| MedCode (Vals AI) | Not measured | 59.1% | Only Gemini 3.1 Pro Preview measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SimpleQA Verified | Not measured | 73.5% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: science | 1446 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: medicine and healthcare | 1440 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: legal and government | 1425 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: business and finance | 1410 | 1459 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1234 | Gemini 3.1 Pro Preview |
| Design Arena: UI components | 1149 | 1226 | Gemini 3.1 Pro Preview |
| Design Arena: game dev | 1132 | 1203 | Gemini 3.1 Pro Preview |
| Design Arena: data viz | 1158 | 1209 | Gemini 3.1 Pro Preview |
| Design Arena: 3D | 1133 | 1234 | Gemini 3.1 Pro Preview |
| Design Arena: all code categories | 1164 | 1231 | Gemini 3.1 Pro Preview |
| Design Arena: SVG | 1032 | 1285 | Gemini 3.1 Pro Preview |
| Design Arena: ASCII art | 1082 | 1270 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index023
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 53.8% | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | Not measured | 48.7% | Only Gemini 3.1 Pro Preview measured |
| MedScribe (Vals AI) | Not measured | 76.1% | Only Gemini 3.1 Pro Preview measured |
| Vals Multimodal Index | Not measured | 56.1% | Only Gemini 3.1 Pro Preview measured |
| IFBench | 60.7% | 77.1% | Gemini 3.1 Pro Preview |
| Long context reasoning (AA-LCR) | 73.3% | 82.0% | Gemini 3.1 Pro Preview |
| DTBench | 85.6% | 97.1% | Gemini 3.1 Pro Preview |
| LMCA | 28.8% | 53.8% | Gemini 3.1 Pro Preview |
| CL-bench | 12.4% | 20.8% | Gemini 3.1 Pro Preview |
| Furniture assembly | Not measured | 26.7% | Only Gemini 3.1 Pro Preview measured |
| ExploitBench | Not measured | 26.1% | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | 7.4% | 16.9% | Gemini 3.1 Pro Preview |
| LMArena Text | 1425 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Text: instruction following | 1413 | 1466 | Gemini 3.1 Pro Preview |
| LMArena Text: creative writing | 1400 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Vision | Not measured | 1296 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: English | 1439 | 1478 | Gemini 3.1 Pro Preview |
| LMArena Text: non-English | 1409 | 1476 | Gemini 3.1 Pro Preview |
| LMArena Text: Chinese | 1455 | 1527 | Gemini 3.1 Pro Preview |
| LMArena Text: German | 1413 | 1490 | Gemini 3.1 Pro Preview |
| LMArena Text: Japanese | 1374 | 1491 | Gemini 3.1 Pro Preview |
| LMArena Text: Korean | 1370 | 1455 | Gemini 3.1 Pro Preview |
| LMArena Text: French | 1429 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: Spanish | 1424 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: Russian | 1424 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: Polish | 1419 | 1498 | Gemini 3.1 Pro Preview |
| LMArena Text: multi-turn | 1427 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: longer queries | 1428 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Text: writing and language | 1407 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: entertainment and media | 1395 | 1465 | Gemini 3.1 Pro Preview |
| LMArena Vision: English | Not measured | 1287 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: Chinese | Not measured | 1364 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: reading text | Not measured | 1304 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: humor | Not measured | 1322 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: captioning | Not measured | 1345 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | Not measured | 1330 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | Not measured | 1324 | Only Gemini 3.1 Pro Preview measured |
| LMArena Document | Not measured | 1444 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | Gemini 3.1 Pro 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
DeepSeek V3.2$0.0005Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request
DeepSeek V3.2 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2$0.015Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request
DeepSeek V3.2 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2$0.060Exceeds the context window
Gemini 3.1 Pro Preview$0.520Fits in one request
DeepSeek V3.2 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 V3.2 | Google Gemini 3.1 Pro Preview |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | February 19, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.28 | $2.00 |
| Output $/Mtok | $0.42 | $12.00 |
| Coding index | 54.4 | 35.3 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.99 | $0.99 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Gemini 3.1 Pro Preview for coding?
Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 35.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview when the context window is larger, 1.05M against 164K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
Which is cheaper, DeepSeek V3.2 or Gemini 3.1 Pro Preview?
DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Gemini 3.1 Pro Preview $0.99.
Which has the bigger context window, DeepSeek V3.2 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Gemini 3.1 Pro Preview comparison based on?
67 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 2 independent benchmarks and Gemini 3.1 Pro Preview's on 1. Where only one model has a result, the page says so instead of naming a winner.