DeepSeek V4 Flash 0731 vs Gemini 3 Flash Preview
Updated October 21, 2026. 40 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 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview.
Pick Gemini 3 Flash Preview when what matters is ALE-Bench or Chess puzzles, where it leads.
- Shared results
- 40
- DeepSeek V4 Flash 0731 only
- 15
- Gemini 3 Flash Preview only
- 29
- 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, six public coding benchmarks
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 scores 51.8 against 43.7.
4 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 26.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash 0731 has a AA Agentic Index result, 41.0.
Directional only
Reasoning
GPQA Diamond
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 89.9% against 87.9%.
Same board, both measured
Math
AIME
No call
Only Gemini 3 Flash Preview has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 1238 against 1196.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, Gemini 3 Flash Preview $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.01, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
- Widest category
- Agentic work, 16.5 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Flash 0731 74.7% against Gemini 3 Flash Preview 20.2%, 54.5 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.396 against Gemini 3 Flash Preview $3.00 per million output tokens, 7.6x 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 Flash 0731 | Bars | Gemini 3 Flash Preview | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 7 | 1 | 1 tie | |
| Math | 3 | 1 | ||
| Knowledge | 0 | 6 | ||
| Web design | 4 | 0 | ||
| General | 3 | 1 | ||
| All shared boards | 28 | 10 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 75.8% | Only Gemini 3 Flash Preview measured |
| AA Coding Index | 69.1 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LiveCodeBench (Vals AI) | 87.3% | 85.6% | DeepSeek V4 Flash 0731 |
| SWE-bench Verified (Vals AI) | 88.8% | 75.0% | DeepSeek V4 Flash 0731 |
| Terminal-Bench 4 (Vals AI) | 18.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Vibe Code Bench (Vals AI) | 74.7% | 20.2% | DeepSeek V4 Flash 0731 |
| Code migration (Vals AI) | 38.6% | 6.4% | DeepSeek V4 Flash 0731 |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | 53.9% | DeepSeek V4 Flash 0731 |
| SkillsBench (Vals AI) | 50.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 90.8% | Only Gemini 3 Flash Preview measured |
| SciCode | 50.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 38.6% | Only Gemini 3 Flash Preview measured |
| Terminal-Bench | Not measured | 64.3% | Only Gemini 3 Flash Preview measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GSO-Bench | Not measured | 9.8% | Only Gemini 3 Flash Preview measured |
| WeirdML | 63.0% | 61.6% | DeepSeek V4 Flash 0731 |
| ALE-Bench | 1306.1 | 1367.2 | Gemini 3 Flash Preview |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 26.3 | DeepSeek V4 Flash 0731 |
| Epoch Capabilities Index | 154.8 | Not measured | Only DeepSeek V4 Flash 0731 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| 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 | 1057 | 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) | 49.5% | 42.5% | DeepSeek V4 Flash 0731 |
| Tax Agent Bench (Vals AI) | 28.1% | 11.8% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 18.3% | DeepSeek V4 Flash 0731 |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 26.0% | DeepSeek V4 Flash 0731 |
| BioMysteryBench (Vals AI) | 64.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| τ²-Bench Telecom | Not measured | 80.4% | Only Gemini 3 Flash Preview 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 | Not measured | $3,635 | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | 87.9% | DeepSeek V4 Flash 0731 |
| MMMU Pro (Vals AI) | Not measured | 87.6% | Only Gemini 3 Flash Preview measured |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 89.8% | DeepSeek V4 Flash 0731 |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 36.6% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Epoch AI run) | 91.0% | 89.4% | DeepSeek V4 Flash 0731 |
| ARC-AGI | 89.0% | 84.7% | DeepSeek V4 Flash 0731 |
| ARC-AGI-2 | 61.4% | 33.6% | DeepSeek V4 Flash 0731 |
| SimpleBench | 61.1% | 61.1% | Tie |
| Chess puzzles | 32.0% | 39.0% | Gemini 3 Flash Preview |
| Mystery game puzzles | 34.0% | 26.0% | DeepSeek V4 Flash 0731 |
| VPCT | Not measured | 72.6% | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only Gemini 3 Flash Preview measured |
| MGSM (Vals AI) | Not measured | 93.3% | Only Gemini 3 Flash Preview measured |
| AA Math Index | Not measured | 97.0 | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 97.0% | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 94.4% | 95.6% | Gemini 3 Flash Preview |
| FrontierMath, tiers 1 to 3 | 57.5% | 51.2% | DeepSeek V4 Flash 0731 |
| FrontierMath, tier 4 | 24.4% | 17.1% | DeepSeek V4 Flash 0731 |
| ProofBench | 56.0% | 15.0% | DeepSeek V4 Flash 0731 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 88.6% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 77.7% | 86.9% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | Not measured | 55.8% | Only Gemini 3 Flash Preview measured |
| CorpFin (Vals AI) | 61.9% | 66.4% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 70.7% | 73.9% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | Not measured | 68.7% | Only Gemini 3 Flash Preview measured |
| MedQA (Vals AI) | Not measured | 95.8% | Only Gemini 3 Flash Preview measured |
| MedCode (Vals AI) | 41.4% | 55.9% | Gemini 3 Flash Preview |
| MMLU Pro (Artificial Analysis run) | Not measured | 89.0% | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 33.6% | 66.8% | Gemini 3 Flash Preview |
| GeoBench | Not measured | 88.0% | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | 1196 | DeepSeek V4 Flash 0731 |
| Design Arena: UI components | 1235 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: game dev | 1208 | 1166 | DeepSeek V4 Flash 0731 |
| Design Arena: data viz | 1180 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: 3D | 1209 | 1184 | DeepSeek V4 Flash 0731 |
| Design Arena: all code categories | 1230 | 1189 | DeepSeek V4 Flash 0731 |
| Design Arena: SVG | 1185 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: ASCII art | 1090 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 51.8% | Only Gemini 3 Flash Preview measured |
| MedScribe (Vals AI) | 80.4% | 69.9% | DeepSeek V4 Flash 0731 |
| Vals Multimodal Index | Not measured | 52.2% | Only Gemini 3 Flash Preview measured |
| IFBench | Not measured | 78.0% | Only Gemini 3 Flash Preview measured |
| Long context reasoning (AA-LCR) | 79.7% | 78.0% | DeepSeek V4 Flash 0731 |
| DTBench | 90.9% | 89.1% | DeepSeek V4 Flash 0731 |
| LMCA | 41.7% | 43.1% | Gemini 3 Flash Preview |
| Neither model has a result on the other 39 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | 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 V4 Flash 0731 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0731 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0731 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 Flash 0731 | Google Gemini 3 Flash Preview |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | July 31, 2026 | December 17, 2025 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.14 | $0.50 |
| Output $/Mtok | $0.396 | $3.00 |
| Coding index | 51.8 | 43.7 |
| Independent measurements behind it | 4 | 2 |
| Cost per solved task | $0.01 | $0.37 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Gemini 3 Flash Preview for coding?
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview. Pick Gemini 3 Flash Preview when what matters is ALE-Bench or Chess puzzles, where it leads.
Which is cheaper, DeepSeek V4 Flash 0731 or Gemini 3 Flash Preview?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.396 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and Gemini 3 Flash Preview $0.37.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Gemini 3 Flash Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Gemini 3 Flash Preview comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 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.