DeepSeek V3.2 vs Gemini 3.8 Flash
Gemini 3.8 Flash leads DeepSeek V3.2 on coding, 61.6 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 4.3x less per output token ($0.88 vs $3.75 per million). Updated October 22, 2026; 59 benchmarks have a result for both.
vs boards won of 59 shared
DeepSeek V3.2 or Gemini 3.8 Flash: which to pick
Pick Gemini 3.8 Flash for coding: it scores 61.6 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.
Pick DeepSeek V3.2 for output tokens 4.3x cheaper ($0.88 vs $3.75 per million) and a lower cost per solved task ($0.99 against $2.74).
Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved task
- Shared results
- 59
- DeepSeek V3.2 only
- 17
- Gemini 3.8 Flash only
- 77
- 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 3.8 Flash
Gemini 3.8 Flash scores 61.6 against 30.0.
3 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 40.9 against 21.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.8 Flash has a AA Agentic Index result, 40.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 94.4% against 80.3%.
Same board, both measured
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 90.2% against 84.9%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 1300 against 1175.
Same board, both measured
General
Vals Index
No call
Only Gemini 3.8 Flash has a Vals Index result, 56.0%.
Directional only
Long documents
Listed context window
Gemini 3.8 Flash
Gemini 3.8 Flash 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 3.8 Flash $0.0026 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V3.2
DeepSeek V3.2 $0.99, Gemini 3.8 Flash $2.74.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, Gemini 3.8 Flash 61.6 from 6 benchmarks.
- Widest category
- Agentic work, 34.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- ARC-AGI-2: DeepSeek V3.2 4.0% against Gemini 3.8 Flash 89.2%, 85.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against Gemini 3.8 Flash $3.75 per million output tokens, 4.3x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Gemini 3.8 Flash 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 3.8 Flash | Ties |
|---|---|---|---|---|
| Coding | 0 | 9 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 8 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 7 | ||
| Web design | 0 | 8 | ||
| General | 0 | 20 | ||
| All shared boards | 0 | 59 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index09
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | 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 |
| LiveBench coding | Not measured | 82.2% | Only Gemini 3.8 Flash measured |
| LMArena WebDev | 1362 | 1585 | Gemini 3.8 Flash |
| AA Coding Index | 44.2 | 76.3 | Gemini 3.8 Flash |
| LiveCodeBench (Vals AI) | 80.7% | 89.5% | Gemini 3.8 Flash |
| SWE-bench Verified (Vals AI) | 67.6% | 80.0% | Gemini 3.8 Flash |
| Terminal-Bench 4 (Vals AI) | Not measured | 19.7% | Only Gemini 3.8 Flash measured |
| Vibe Code Bench (Vals AI) | 5.1% | 78.7% | Gemini 3.8 Flash |
| Code migration (Vals AI) | Not measured | 36.5% | Only Gemini 3.8 Flash measured |
| ProgramBench (Vals AI) | Not measured | 1.0% | Only Gemini 3.8 Flash measured |
| IOI (Vals AI) | Not measured | 56.9% | Only Gemini 3.8 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 81.3% | Only Gemini 3.8 Flash measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Gemini 3.8 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 18.8% | Only Gemini 3.8 Flash measured |
| SkillsBench (Vals AI) | Not measured | 58.0% | Only Gemini 3.8 Flash measured |
| CyberBench (Vals AI) | Not measured | 43.8% | Only Gemini 3.8 Flash measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 56.6% | Only Gemini 3.8 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| FrontierCode | Not measured | 41.2% | Only Gemini 3.8 Flash measured |
| FrontierSWE | Not measured | 19.6% | Only Gemini 3.8 Flash measured |
| WeirdML | Not measured | 84.8% | Only Gemini 3.8 Flash measured |
| ALE-Bench | Not measured | 1269.7 | Only Gemini 3.8 Flash measured |
| LMArena Text: coding | 1453 | 1508 | Gemini 3.8 Flash |
| LMArena Text: software and IT | 1449 | 1507 | Gemini 3.8 Flash |
| LMArena WebDev: React | 1350 | 1577 | Gemini 3.8 Flash |
| LMArena WebDev: HTML | 1371 | 1616 | Gemini 3.8 Flash |
| LMArena WebDev: from an image | Not measured | 1593 | Only Gemini 3.8 Flash measured |
| SciCode | Not measured | 12.3% | Only Gemini 3.8 Flash measured |
| SWE-Bench Pro V2 | Not measured | 94.9% | Only Gemini 3.8 Flash measured |
| SWE Atlas: Codebase QnA | Not measured | 47.0% | Only Gemini 3.8 Flash measured |
| SWE Atlas: Refactoring | Not measured | 44.8% | Only Gemini 3.8 Flash measured |
| SWE Atlas: Test Writing | Not measured | 53.7% | Only Gemini 3.8 Flash measured |
| Neither model has a result on the other 8 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 40.9 | Gemini 3.8 Flash |
| Epoch Capabilities Index | 146.1 | 157.4 | Gemini 3.8 Flash |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 40.2 | Only Gemini 3.8 Flash measured |
| Design Arena: agents building web apps | Not measured | 1238 | Only Gemini 3.8 Flash measured |
| Design Arena: agents building full-stack apps | Not measured | 1244 | Only Gemini 3.8 Flash measured |
| Design Arena: agents building mobile apps | Not measured | 1236 | Only Gemini 3.8 Flash measured |
| Design Arena: agents building Android apps | Not measured | 1078 | Only Gemini 3.8 Flash measured |
| Design Arena: agents building Godot games | Not measured | 1273 | Only Gemini 3.8 Flash measured |
| Design Arena: PowerPoint slides | Not measured | 1152 | Only Gemini 3.8 Flash measured |
| Design Arena: spreadsheets | Not measured | 1037 | Only Gemini 3.8 Flash measured |
| LiveBench research | Not measured | 79.1% | Only Gemini 3.8 Flash measured |
| LiveBench browser | Not measured | 64.0% | Only Gemini 3.8 Flash measured |
| LiveBench long agentic | Not measured | 30.1% | Only Gemini 3.8 Flash measured |
| SREBench (Vals AI) | Not measured | 11.1% | Only Gemini 3.8 Flash measured |
| Finance Agent (Vals AI) | Not measured | 61.4% | Only Gemini 3.8 Flash measured |
| Tax Agent Bench (Vals AI) | Not measured | 32.1% | Only Gemini 3.8 Flash measured |
| Legal Research Bench (Vals AI) | Not measured | 38.9% | Only Gemini 3.8 Flash measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.1% | Only Gemini 3.8 Flash measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 72.2% | Only Gemini 3.8 Flash measured |
| BioMysteryBench (Vals AI) | Not measured | 62.2% | Only Gemini 3.8 Flash measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 8.6% | Only Gemini 3.8 Flash measured |
| Vals Science Index | Not measured | 35.8% | Only Gemini 3.8 Flash measured |
| Time Horizon Index (Vals AI) | Not measured | 18.8% | Only Gemini 3.8 Flash measured |
| CUA-bench (Vals AI) | Not measured | 4.2% | Only Gemini 3.8 Flash measured |
| τ²-Bench Telecom | 90.6% | Not measured | Only DeepSeek V3.2 measured |
| APEX-Agents | 21.3% | 64.3% | Gemini 3.8 Flash |
| Remote Labor Index | Not measured | 5.8% | Only Gemini 3.8 Flash measured |
| Vending-Bench 2 | $1,034 | $5,094 | Gemini 3.8 Flash |
| Neither model has a result on the other 16 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 94.4% | Gemini 3.8 Flash |
| LiveBench reasoning | Not measured | 89.3% | Only Gemini 3.8 Flash measured |
| MysteryMechanism (Vals AI) | Not measured | 36.5% | Only Gemini 3.8 Flash measured |
| MMMU Pro (Vals AI) | Not measured | 89.1% | Only Gemini 3.8 Flash measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 95.3% | Gemini 3.8 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 47.8% | Gemini 3.8 Flash |
| GPQA Diamond (Epoch AI run) | Not measured | 95.4% | Only Gemini 3.8 Flash measured |
| ARC-AGI | 57.0% | 98.5% | Gemini 3.8 Flash |
| ARC-AGI-2 | 4.0% | 89.2% | Gemini 3.8 Flash |
| Chess puzzles | Not measured | 58.0% | Only Gemini 3.8 Flash measured |
| Mystery game puzzles | Not measured | 47.0% | Only Gemini 3.8 Flash measured |
| LMArena Text: hard prompts | 1434 | 1509 | Gemini 3.8 Flash |
| LMArena Text: expert | 1436 | 1526 | Gemini 3.8 Flash |
| LMArena Text: hard prompts in English | 1446 | 1504 | Gemini 3.8 Flash |
| LMArena Vision: diagrams | Not measured | 1345 | Only Gemini 3.8 Flash measured |
| LMArena Vision: homework | Not measured | 1351 | Only Gemini 3.8 Flash measured |
| Humanity's Last Exam (Scale run) | Not measured | 34.3% | Only Gemini 3.8 Flash measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| 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 | 98.9% | Only Gemini 3.8 Flash measured |
| FrontierMath, tiers 1 to 3 | Not measured | 68.4% | Only Gemini 3.8 Flash measured |
| FrontierMath, tier 4 | Not measured | 22.0% | Only Gemini 3.8 Flash measured |
| ProofBench | Not measured | 48.0% | Only Gemini 3.8 Flash measured |
| LMArena Text: math | 1435 | 1532 | Gemini 3.8 Flash |
| LMArena Text: mathematical work | 1440 | 1519 | Gemini 3.8 Flash |
| MathArena | 16.0% | 34.0% | Gemini 3.8 Flash |
| 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 3.8 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 90.2% | Gemini 3.8 Flash |
| LegalBench (Vals AI) | 76.1% | 87.0% | Gemini 3.8 Flash |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | Not measured | Only DeepSeek V3.2 measured |
| TaxEval (Vals AI) | 68.2% | 74.5% | Gemini 3.8 Flash |
| MortgageTax (Vals AI) | Not measured | 65.3% | Only Gemini 3.8 Flash measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MedCode (Vals AI) | Not measured | 48.1% | Only Gemini 3.8 Flash measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SimpleQA Verified | Not measured | 69.7% | Only Gemini 3.8 Flash measured |
| LMArena Text: science | 1446 | 1523 | Gemini 3.8 Flash |
| LMArena Text: medicine and healthcare | 1440 | 1508 | Gemini 3.8 Flash |
| LMArena Text: legal and government | 1425 | 1497 | Gemini 3.8 Flash |
| LMArena Text: business and finance | 1410 | 1479 | Gemini 3.8 Flash |
| FACTS Benchmark Suite | Not measured | 69.4% | Only Gemini 3.8 Flash measured |
| PRBench Finance | Not measured | 49.5% | Only Gemini 3.8 Flash measured |
| PRBench Legal | Not measured | 48.9% | Only Gemini 3.8 Flash measured |
| 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 3.8 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1300 | Gemini 3.8 Flash |
| Design Arena: UI components | 1146 | 1316 | Gemini 3.8 Flash |
| Design Arena: game dev | 1131 | 1304 | Gemini 3.8 Flash |
| Design Arena: data viz | 1159 | 1271 | Gemini 3.8 Flash |
| Design Arena: 3D | 1132 | 1294 | Gemini 3.8 Flash |
| Design Arena: all code categories | 1163 | 1303 | Gemini 3.8 Flash |
| Design Arena: SVG | 1031 | 1295 | Gemini 3.8 Flash |
| Design Arena: ASCII art | 1082 | 1264 | Gemini 3.8 Flash |
| LiveBench design | Not measured | 72.7% | Only Gemini 3.8 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
| Benchmark | DeepSeek V3.2 | Gemini 3.8 Flash | Leader |
|---|---|---|---|
| Vals Index | Not measured | 56.0% | Only Gemini 3.8 Flash measured |
| LiveBench data analysis | Not measured | 54.0% | Only Gemini 3.8 Flash measured |
| Public Benefits Bench (Vals AI) | Not measured | 65.3% | Only Gemini 3.8 Flash measured |
| SAGE (Vals AI) | Not measured | 35.1% | Only Gemini 3.8 Flash measured |
| MedScribe (Vals AI) | Not measured | 84.5% | Only Gemini 3.8 Flash measured |
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | 84.0% | Gemini 3.8 Flash |
| DTBench | 85.6% | 95.7% | Gemini 3.8 Flash |
| LMCA | 28.8% | 52.9% | Gemini 3.8 Flash |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| Surface Evolver Bench | Not measured | 76.9% | Only Gemini 3.8 Flash measured |
| Furniture assembly | Not measured | 31.7% | Only Gemini 3.8 Flash measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | 1499 | Gemini 3.8 Flash |
| LMArena Text: instruction following | 1413 | 1492 | Gemini 3.8 Flash |
| LMArena Text: creative writing | 1400 | 1488 | Gemini 3.8 Flash |
| LMArena Vision | Not measured | 1315 | Only Gemini 3.8 Flash measured |
| LMArena Text: English | 1439 | 1498 | Gemini 3.8 Flash |
| LMArena Text: non-English | 1409 | 1491 | Gemini 3.8 Flash |
| LMArena Text: Chinese | 1455 | 1553 | Gemini 3.8 Flash |
| LMArena Text: German | 1413 | 1501 | Gemini 3.8 Flash |
| LMArena Text: Japanese | 1374 | 1507 | Gemini 3.8 Flash |
| LMArena Text: Korean | 1370 | 1464 | Gemini 3.8 Flash |
| LMArena Text: French | 1429 | 1496 | Gemini 3.8 Flash |
| LMArena Text: Spanish | 1424 | 1487 | Gemini 3.8 Flash |
| LMArena Text: Russian | 1424 | 1514 | Gemini 3.8 Flash |
| LMArena Text: Polish | 1419 | 1497 | Gemini 3.8 Flash |
| LMArena Text: multi-turn | 1427 | 1503 | Gemini 3.8 Flash |
| LMArena Text: longer queries | 1428 | 1507 | Gemini 3.8 Flash |
| LMArena Text: writing and language | 1407 | 1494 | Gemini 3.8 Flash |
| LMArena Text: entertainment and media | 1395 | 1480 | Gemini 3.8 Flash |
| LMArena Vision: English | Not measured | 1318 | Only Gemini 3.8 Flash measured |
| LMArena Vision: Chinese | Not measured | 1416 | Only Gemini 3.8 Flash measured |
| LMArena Vision: reading text | Not measured | 1333 | Only Gemini 3.8 Flash measured |
| LMArena Vision: humor | Not measured | 1321 | Only Gemini 3.8 Flash measured |
| LMArena Vision: creative writing | Not measured | 1299 | Only Gemini 3.8 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 V3.2 | Gemini 3.8 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 V3.2$0.0007Fits in one request
Gemini 3.8 Flash$0.0026Fits in one request
DeepSeek V3.2 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2$0.017Fits in one request
Gemini 3.8 Flash$0.049Fits in one request
DeepSeek V3.2 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2$0.067Exceeds the context window
Gemini 3.8 Flash$0.188Fits 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 3.8 Flash |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | September 2, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.29 | $0.75 |
| Output $/Mtok | $0.88 | $3.75 |
| Coding index | 30.0 | 61.6 |
| Independent measurements behind it | 3 | 6 |
| Cost per solved task | $0.99 | $2.74 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Gemini 3.8 Flash for coding?
Pick Gemini 3.8 Flash for coding: it scores 61.6 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 4.3x cheaper ($0.88 vs $3.75 per million) and a lower cost per solved task ($0.99 against $2.74).
Which is cheaper, DeepSeek V3.2 or Gemini 3.8 Flash?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Gemini 3.8 Flash $2.74.
Which has the bigger context window, DeepSeek V3.2 or Gemini 3.8 Flash?
Gemini 3.8 Flash, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Gemini 3.8 Flash comparison based on?
59 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Gemini 3.8 Flash's on 6. Where only one model has a result, the page says so instead of naming a winner.