DeepSeek V3.1 vs Gemini 2.5 Flash
Gemini 2.5 Flash leads DeepSeek V3.1 on the Artificial Analysis Intelligence Index, 15.5 to 13.7, and DeepSeek V3.1 costs 1.7x less per output token ($1.50 vs $2.50 per million). Updated October 21, 2026; 11 benchmarks have a result for both.
DeepSeek V3.1 or Gemini 2.5 Flash: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3.1 for output tokens 1.7x cheaper ($1.50 vs $2.50 per million) and work measured by AA Intelligence Index or Kagi LLM Benchmark, where it leads.
- Shared results
- 11
- DeepSeek V3.1 only
- 0
- Gemini 2.5 Flash only
- 62
- Like-for-like categories
- 4 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Gemini 2.5 Flash
Gemini 2.5 Flash leads, 15.5 against 13.7.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V3.1
DeepSeek V3.1 leads, 1123 against 1074.
Same board, both measured
Long documents
Listed context window
Gemini 2.5 Flash
Gemini 2.5 Flash takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.1
DeepSeek V3.1 $0.0013, Gemini 2.5 Flash $0.0015 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 2.5 Flash has the number, $0.466.
Directional only
At a glance
- Coding index
- DeepSeek V3.1 not benchmarked, Gemini 2.5 Flash not benchmarked.
- Widest category
- Web design, 7.2 points apart on average over 7 shared benchmarks.
- Widest single gap
- Design Arena: UI components: DeepSeek V3.1 1085 against Gemini 2.5 Flash 1005, 10.0 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.1 $1.50 against Gemini 2.5 Flash $2.50 per million output tokens, 1.7x apart.
- Context window
- DeepSeek V3.1 takes 164K tokens, Gemini 2.5 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 V3.1 | Bars | Gemini 2.5 Flash | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Web design | 6 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 7 | 4 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 28.7% | Only Gemini 2.5 Flash measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 69.5% | Only Gemini 2.5 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 13.6% | Only Gemini 2.5 Flash measured |
| Terminal-Bench | Not measured | 17.1% | Only Gemini 2.5 Flash measured |
| LMArena Text: coding | Not measured | 1423 | Only Gemini 2.5 Flash measured |
| LMArena Text: software and IT | Not measured | 1425 | Only Gemini 2.5 Flash measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.7 | 15.5 | Gemini 2.5 Flash |
| Epoch Capabilities Index | Not measured | 142.9 | Only Gemini 2.5 Flash measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 31.6% | Only Gemini 2.5 Flash measured |
| BALROG | Not measured | 33.5% | Only Gemini 2.5 Flash measured |
| Vending-Bench 2 | Not measured | $549 | Only Gemini 2.5 Flash measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 56.2% | Only Gemini 2.5 Flash measured |
| BrowseComp-Plus | Not measured | 39.9% | Only Gemini 2.5 Flash measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 79.0% | Only Gemini 2.5 Flash measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 12.1% | Only Gemini 2.5 Flash measured |
| ARC-AGI | Not measured | 33.3% | Only Gemini 2.5 Flash measured |
| ARC-AGI-2 | Not measured | 2.5% | Only Gemini 2.5 Flash measured |
| SimpleBench | Not measured | 41.2% | Only Gemini 2.5 Flash measured |
| LMArena Text: hard prompts | Not measured | 1422 | Only Gemini 2.5 Flash measured |
| LMArena Text: expert | Not measured | 1426 | Only Gemini 2.5 Flash measured |
| LMArena Text: hard prompts in English | Not measured | 1420 | Only Gemini 2.5 Flash measured |
| LMArena Vision: diagrams | Not measured | 1245 | Only Gemini 2.5 Flash measured |
| LMArena Vision: homework | Not measured | 1244 | Only Gemini 2.5 Flash measured |
| Kagi LLM Benchmark | 53.2% | 56.8% | Gemini 2.5 Flash |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 73.3 | Only Gemini 2.5 Flash measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 73.3% | Only Gemini 2.5 Flash measured |
| LMArena Text: math | Not measured | 1411 | Only Gemini 2.5 Flash measured |
| LMArena Text: mathematical work | Not measured | 1422 | Only Gemini 2.5 Flash measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 40.4% | Only Gemini 2.5 Flash measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 83.2% | Only Gemini 2.5 Flash measured |
| LMArena Text: science | Not measured | 1433 | Only Gemini 2.5 Flash measured |
| LMArena Text: medicine and healthcare | Not measured | 1428 | Only Gemini 2.5 Flash measured |
| LMArena Text: legal and government | Not measured | 1430 | Only Gemini 2.5 Flash measured |
| LMArena Text: business and finance | Not measured | 1404 | Only Gemini 2.5 Flash measured |
| FACTS Benchmark Suite | Not measured | 47.2% | Only Gemini 2.5 Flash measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1123 | 1074 | DeepSeek V3.1 |
| Design Arena: UI components | 1085 | 1005 | DeepSeek V3.1 |
| Design Arena: game dev | 1084 | 1005 | DeepSeek V3.1 |
| Design Arena: data viz | 1095 | 1060 | DeepSeek V3.1 |
| Design Arena: 3D | 1077 | 1021 | DeepSeek V3.1 |
| Design Arena: all code categories | 1112 | 1059 | DeepSeek V3.1 |
| Design Arena: SVG | 967 | 1020 | Gemini 2.5 Flash |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V3.1 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 44.8% | Only Gemini 2.5 Flash measured |
| MedScribe (Vals AI) | Not measured | 83.0% | Only Gemini 2.5 Flash measured |
| IFBench | Not measured | 50.3% | Only Gemini 2.5 Flash measured |
| Long context reasoning (AA-LCR) | Not measured | 65.3% | Only Gemini 2.5 Flash measured |
| DTBench | 82.7% | 76.5% | DeepSeek V3.1 |
| LMCA | 24.3% | 27.5% | Gemini 2.5 Flash |
| LMArena Text | Not measured | 1417 | Only Gemini 2.5 Flash measured |
| LMArena Text: instruction following | Not measured | 1405 | Only Gemini 2.5 Flash measured |
| LMArena Text: creative writing | Not measured | 1400 | Only Gemini 2.5 Flash measured |
| LMArena Vision | Not measured | 1235 | Only Gemini 2.5 Flash measured |
| LMArena Text: English | Not measured | 1418 | Only Gemini 2.5 Flash measured |
| LMArena Text: non-English | Not measured | 1409 | Only Gemini 2.5 Flash measured |
| LMArena Text: Chinese | Not measured | 1449 | Only Gemini 2.5 Flash measured |
| LMArena Text: German | Not measured | 1417 | Only Gemini 2.5 Flash measured |
| LMArena Text: Japanese | Not measured | 1396 | Only Gemini 2.5 Flash measured |
| LMArena Text: Korean | Not measured | 1385 | Only Gemini 2.5 Flash measured |
| LMArena Text: French | Not measured | 1432 | Only Gemini 2.5 Flash measured |
| LMArena Text: Spanish | Not measured | 1422 | Only Gemini 2.5 Flash measured |
| LMArena Text: Russian | Not measured | 1415 | Only Gemini 2.5 Flash measured |
| LMArena Text: Polish | Not measured | 1413 | Only Gemini 2.5 Flash measured |
| LMArena Text: multi-turn | Not measured | 1408 | Only Gemini 2.5 Flash measured |
| LMArena Text: longer queries | Not measured | 1419 | Only Gemini 2.5 Flash measured |
| LMArena Text: writing and language | Not measured | 1405 | Only Gemini 2.5 Flash measured |
| LMArena Text: entertainment and media | Not measured | 1393 | Only Gemini 2.5 Flash measured |
| LMArena Vision: English | Not measured | 1239 | Only Gemini 2.5 Flash measured |
| LMArena Vision: Chinese | Not measured | 1284 | Only Gemini 2.5 Flash measured |
| LMArena Vision: reading text | Not measured | 1237 | Only Gemini 2.5 Flash measured |
| LMArena Vision: humor | Not measured | 1225 | Only Gemini 2.5 Flash measured |
| LMArena Vision: captioning | Not measured | 1277 | Only Gemini 2.5 Flash measured |
| LMArena Vision: recognizing things | Not measured | 1252 | Only Gemini 2.5 Flash measured |
| LMArena Vision: creative writing | Not measured | 1241 | Only Gemini 2.5 Flash measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.1 | Gemini 2.5 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 V3.1 costs less
Repository review
50K input + 3K output tokens
Gemini 2.5 Flash costs less
Agent loop
200K input + 10K output tokens
Gemini 2.5 Flash 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 V3.1 | Google Gemini 2.5 Flash |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | August 21, 2025 | June 17, 2025 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.55 | $0.30 |
| Output $/Mtok | $1.50 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | $0.466 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.1 better than Gemini 2.5 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 for output tokens 1.7x cheaper ($1.50 vs $2.50 per million) and work measured by AA Intelligence Index or Kagi LLM Benchmark, where it leads.
Which is cheaper, DeepSeek V3.1 or Gemini 2.5 Flash?
DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; Gemini 2.5 Flash costs $0.30 and $2.50. Cost per solved task is known for Gemini 2.5 Flash only.
Which has the bigger context window, DeepSeek V3.1 or Gemini 2.5 Flash?
Gemini 2.5 Flash, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.1 vs Gemini 2.5 Flash comparison based on?
11 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1's coding index rests on 0 independent benchmarks and Gemini 2.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.