DeepSeek V3.2 vs Gemini 3 Flash Preview
Gemini 3 Flash Preview leads DeepSeek V3.2 on coding, 43.7 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 3.4x less per output token ($0.88 vs $3.00 per million). Updated October 21, 2026; 34 benchmarks have a result for both.
DeepSeek V3.2 or Gemini 3 Flash Preview: which to pick
Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 30.0 for DeepSeek V3.2, though on 2 benchmarks against 3.
Pick DeepSeek V3.2 for output tokens 3.4x cheaper ($0.88 vs $3.00 per million) and work measured by τ²-Bench Telecom, where it leads.
- Shared results
- 34
- DeepSeek V3.2 only
- 41
- Gemini 3 Flash Preview only
- 37
- 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 3 Flash Preview
Gemini 3 Flash Preview scores 43.7 against 30.0.
3 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 26.3 against 21.5.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 87.9% against 80.3%.
Same board, both measured
Math
AIME
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 95.6% against 84.6%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 84.9%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 1196 against 1175.
Same board, both measured
Long documents
Listed context window
Gemini 3 Flash Preview
Gemini 3 Flash Preview takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, Gemini 3 Flash Preview $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
DeepSeek V3.2 $0.99, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
- Widest category
- Reasoning, 16.5 points apart on average over 5 shared benchmarks.
- Widest single gap
- ARC-AGI-2: DeepSeek V3.2 4.0% against Gemini 3 Flash Preview 33.6%, 29.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against Gemini 3 Flash Preview $3.00 per million output tokens, 3.4x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Gemini 3 Flash 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 Flash Preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 4 | ||
| Knowledge | 0 | 7 | ||
| Web design | 0 | 4 | ||
| General | 0 | 4 | ||
| All shared boards | 1 | 33 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | 75.8% | Gemini 3 Flash Preview |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | Not measured | Only DeepSeek V3.2 measured |
| AA Coding Index | 44.2 | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Vals AI) | 80.7% | 85.6% | Gemini 3 Flash Preview |
| SWE-bench Verified (Vals AI) | 67.6% | 75.0% | Gemini 3 Flash Preview |
| Vibe Code Bench (Vals AI) | 5.1% | 20.2% | Gemini 3 Flash Preview |
| Code migration (Vals AI) | Not measured | 6.4% | Only Gemini 3 Flash Preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Gemini 3 Flash Preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.9% | Only Gemini 3 Flash Preview measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | 90.8% | Gemini 3 Flash Preview |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | 38.6% | Gemini 3 Flash Preview |
| Terminal-Bench | 39.6% | 64.3% | Gemini 3 Flash Preview |
| GSO-Bench | Not measured | 9.8% | Only Gemini 3 Flash Preview measured |
| WeirdML | Not measured | 61.6% | Only Gemini 3 Flash Preview measured |
| ALE-Bench | Not measured | 1367.2 | Only Gemini 3 Flash Preview measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: HTML | 1371 | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 12.7% | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 26.3 | Gemini 3 Flash 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 index11
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1110 | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building full-stack apps | Not measured | 1063 | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building mobile apps | Not measured | 1090 | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building Android apps | Not measured | 1050 | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building Godot games | Not measured | 1161 | Only Gemini 3 Flash Preview measured |
| Design Arena: PowerPoint slides | Not measured | 1036 | Only Gemini 3 Flash Preview measured |
| Finance Agent (Vals AI) | Not measured | 42.5% | Only Gemini 3 Flash Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 11.8% | Only Gemini 3 Flash Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 18.3% | Only Gemini 3 Flash Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 26.0% | Only Gemini 3 Flash Preview measured |
| τ²-Bench Telecom | 90.6% | 80.4% | DeepSeek V3.2 |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| BALROG | Not measured | 48.1% | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | Not measured | 49.8% | Only Gemini 3 Flash Preview measured |
| Vending-Bench 2 | $1,034 | $3,635 | Gemini 3 Flash Preview |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 87.9% | Gemini 3 Flash Preview |
| MMMU Pro (Vals AI) | Not measured | 87.6% | Only Gemini 3 Flash Preview measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 89.8% | Gemini 3 Flash Preview |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 36.6% | Gemini 3 Flash Preview |
| GPQA Diamond (Epoch AI run) | Not measured | 89.4% | Only Gemini 3 Flash Preview measured |
| ARC-AGI | 57.0% | 84.7% | Gemini 3 Flash Preview |
| ARC-AGI-2 | 4.0% | 33.6% | Gemini 3 Flash Preview |
| SimpleBench | Not measured | 61.1% | Only Gemini 3 Flash Preview measured |
| Chess puzzles | Not measured | 39.0% | Only Gemini 3 Flash Preview measured |
| Mystery game puzzles | Not measured | 26.0% | Only Gemini 3 Flash Preview measured |
| VPCT | Not measured | 72.6% | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | 1434 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AIME | 84.6% | 95.6% | Gemini 3 Flash Preview |
| MGSM (Vals AI) | 86.0% | 93.3% | Gemini 3 Flash Preview |
| AA Math Index | 92.0 | 97.0 | Gemini 3 Flash Preview |
| AIME 2025 (Artificial Analysis run) | 92.0% | 97.0% | Gemini 3 Flash Preview |
| OTIS Mock AIME | Not measured | 95.6% | Only Gemini 3 Flash Preview measured |
| FrontierMath, tiers 1 to 3 | Not measured | 51.2% | Only Gemini 3 Flash Preview measured |
| FrontierMath, tier 4 | Not measured | 17.1% | Only Gemini 3 Flash Preview measured |
| ProofBench | Not measured | 15.0% | Only Gemini 3 Flash Preview measured |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 88.6% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 76.1% | 86.9% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | 55.4% | 55.8% | Gemini 3 Flash Preview |
| CorpFin (Vals AI) | 51.0% | 66.4% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 68.2% | 73.9% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | Not measured | 68.7% | Only Gemini 3 Flash Preview measured |
| MedQA (Vals AI) | 93.9% | 95.8% | Gemini 3 Flash Preview |
| MedCode (Vals AI) | Not measured | 55.9% | Only Gemini 3 Flash Preview measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | 89.0% | Gemini 3 Flash Preview |
| SimpleQA Verified | Not measured | 66.8% | Only Gemini 3 Flash Preview measured |
| GeoBench | Not measured | 88.0% | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| FACTS Benchmark Suite | Not measured | 63.4% | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1196 | Gemini 3 Flash Preview |
| Design Arena: UI components | 1149 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: game dev | 1132 | 1166 | Gemini 3 Flash Preview |
| Design Arena: data viz | 1158 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: 3D | 1133 | 1184 | Gemini 3 Flash Preview |
| Design Arena: all code categories | 1164 | 1189 | Gemini 3 Flash Preview |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1083 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.2 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 51.8% | Only Gemini 3 Flash Preview measured |
| MedScribe (Vals AI) | Not measured | 69.9% | Only Gemini 3 Flash Preview measured |
| Vals Multimodal Index | Not measured | 52.2% | Only Gemini 3 Flash Preview measured |
| IFBench | 60.7% | 78.0% | Gemini 3 Flash Preview |
| Long context reasoning (AA-LCR) | 73.3% | 78.0% | Gemini 3 Flash Preview |
| DTBench | 85.6% | 89.1% | Gemini 3 Flash Preview |
| LMCA | 28.8% | 43.1% | Gemini 3 Flash Preview |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 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 V3.2 | Gemini 3 Flash 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 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 costs less
Agent loop
200K input + 10K output tokens
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 Flash Preview |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | December 17, 2025 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.29 | $0.50 |
| Output $/Mtok | $0.88 | $3.00 |
| Coding index | 30.0 | 43.7 |
| Independent measurements behind it | 3 | 2 |
| Cost per solved task | $0.99 | $0.37 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Gemini 3 Flash Preview for coding?
Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 30.0 for DeepSeek V3.2, though on 2 benchmarks against 3. Pick DeepSeek V3.2 for output tokens 3.4x cheaper ($0.88 vs $3.00 per million) and work measured by τ²-Bench Telecom, where it leads.
Which is cheaper, DeepSeek V3.2 or Gemini 3 Flash Preview?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Gemini 3 Flash Preview $0.37.
Which has the bigger context window, DeepSeek V3.2 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Gemini 3 Flash Preview comparison based on?
34 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Gemini 3 Flash Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.