DeepSeek V4 Flash 0731 vs Gemini 4 Argon
Gemini 4 Argon leads DeepSeek V4 Flash 0731 on coding, 81.0 to 51.8 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 35.7x less per output token ($0.28 vs $10.00 per million). Updated October 21, 2026; 41 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Gemini 4 Argon: which to pick
Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731.
Pick DeepSeek V4 Flash 0731 for output tokens 35.7x cheaper ($0.28 vs $10.00 per million) and work measured by Terminal-Bench 2.1 (Vals AI), where it leads.
- Shared results
- 41
- DeepSeek V4 Flash 0731 only
- 14
- Gemini 4 Argon only
- 52
- 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 4 Argon
Gemini 4 Argon scores 81.0 against 51.8.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 4 Argon
Gemini 4 Argon leads, 52.6 against 34.3.
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
No call
Only DeepSeek V4 Flash 0731 has a GPQA Diamond result, 89.9%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Flash 0731 has a MMLU Pro result, 86.2%.
Directional only
Web design
Design Arena: websites
Gemini 4 Argon
Gemini 4 Argon leads, 1315 against 1238.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Argon has a Vals Index result, 69.2%.
Directional only
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 4 Argon $0.0070 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Flash 0731 has the number, $0.01.
Directional only
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Gemini 4 Argon 81.0 from 5 benchmarks.
- Widest category
- Math, 32.7 points apart on average over 4 shared benchmarks.
- Widest single gap
- IOI (Vals AI): DeepSeek V4 Flash 0731 32.7% against Gemini 4 Argon 100.0%, 67.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against Gemini 4 Argon $10.00 per million output tokens, 35.7x 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 4 Argon | Ties |
|---|---|---|---|---|
| Coding | 1 | 9 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 6 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 4 | ||
| Knowledge | 0 | 3 | ||
| Web design | 0 | 6 | ||
| General | 0 | 3 | 1 tie | |
| All shared boards | 1 | 39 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index19
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 89.7% | Only Gemini 4 Argon measured |
| LMArena WebDev | Not measured | 1678 | Only Gemini 4 Argon measured |
| AA Coding Index | 69.1 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LiveCodeBench (Vals AI) | 87.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Verified (Vals AI) | 88.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 4 (Vals AI) | 18.7% | 57.6% | Gemini 4 Argon |
| Vibe Code Bench (Vals AI) | 74.7% | 91.9% | Gemini 4 Argon |
| Code migration (Vals AI) | 38.6% | 68.2% | Gemini 4 Argon |
| ProgramBench (Vals AI) | 0.0% | 2.5% | Gemini 4 Argon |
| IOI (Vals AI) | 32.7% | 100.0% | Gemini 4 Argon |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | 57.7% | DeepSeek V4 Flash 0731 |
| SWE-bench Multimodal (Vals AI) | Not measured | 56.0% | Only Gemini 4 Argon measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 21.2% | Only Gemini 4 Argon measured |
| SkillsBench (Vals AI) | 50.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | 72.1% | 77.9% | Gemini 4 Argon |
| SciCode | 50.3% | 61.8% | Gemini 4 Argon |
| FrontierCode | 18.8% | 47.5% | Gemini 4 Argon |
| FrontierSWE | Not measured | 55.0% | Only Gemini 4 Argon measured |
| WeirdML | 63.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 1306.1 | 2100.1 | Gemini 4 Argon |
| LMArena Text: coding | Not measured | 1546 | Only Gemini 4 Argon measured |
| LMArena Text: software and IT | Not measured | 1556 | Only Gemini 4 Argon measured |
| LMArena WebDev: React | Not measured | 1692 | Only Gemini 4 Argon measured |
| LMArena WebDev: HTML | Not measured | 1643 | Only Gemini 4 Argon measured |
| SciCode | Not measured | 12.3% | Only Gemini 4 Argon measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 52.6 | Gemini 4 Argon |
| Epoch Capabilities Index | 154.8 | 166.4 | Gemini 4 Argon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: spreadsheets | Not measured | 1142 | Only Gemini 4 Argon measured |
| LiveBench research | Not measured | 83.1% | Only Gemini 4 Argon measured |
| LiveBench browser | Not measured | 92.0% | Only Gemini 4 Argon measured |
| LiveBench long agentic | Not measured | 69.9% | Only Gemini 4 Argon measured |
| SREBench (Vals AI) | Not measured | 44.3% | Only Gemini 4 Argon measured |
| Finance Agent (Vals AI) | 49.5% | 65.4% | Gemini 4 Argon |
| Tax Agent Bench (Vals AI) | 28.1% | 44.6% | Gemini 4 Argon |
| Legal Research Bench (Vals AI) | 30.3% | 54.8% | Gemini 4 Argon |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 27.1% | Only Gemini 4 Argon measured |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 75.2% | Gemini 4 Argon |
| BioMysteryBench (Vals AI) | 64.4% | 76.3% | Gemini 4 Argon |
| Terminal-Bench-Science (Vals AI) | 4.3% | 44.3% | Gemini 4 Argon |
| Vals Science Index | Not measured | 55.4% | Only Gemini 4 Argon measured |
| Time Horizon Index (Vals AI) | Not measured | 52.5% | Only Gemini 4 Argon measured |
| CUA-bench (Vals AI) | Not measured | 4.8% | Only Gemini 4 Argon measured |
| Robo-bench (Vals AI) | Not measured | 0.8% | Only Gemini 4 Argon measured |
| APEX-Agents | Not measured | 82.4% | Only Gemini 4 Argon measured |
| Vending-Bench 2 | Not measured | $13,718 | Only Gemini 4 Argon measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LiveBench reasoning | Not measured | 95.1% | Only Gemini 4 Argon measured |
| MysteryMechanism (Vals AI) | Not measured | 45.5% | Only Gemini 4 Argon measured |
| GPQA Diamond (Artificial Analysis run) | 90.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 57.1% | Gemini 4 Argon |
| GPQA Diamond (Epoch AI run) | 91.0% | 96.4% | Gemini 4 Argon |
| ARC-AGI | 89.0% | 98.5% | Gemini 4 Argon |
| ARC-AGI-2 | 61.4% | 91.3% | Gemini 4 Argon |
| SimpleBench | 61.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Chess puzzles | 32.0% | 59.0% | Gemini 4 Argon |
| Mystery game puzzles | 34.0% | 64.0% | Gemini 4 Argon |
| EBR-bench | Not measured | 64.8% | Only Gemini 4 Argon measured |
| LMArena Text: hard prompts | Not measured | 1546 | Only Gemini 4 Argon measured |
| LMArena Text: expert | Not measured | 1550 | Only Gemini 4 Argon measured |
| LMArena Text: hard prompts in English | Not measured | 1548 | Only Gemini 4 Argon measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | 100.0% | Gemini 4 Argon |
| FrontierMath, tiers 1 to 3 | 57.5% | 86.0% | Gemini 4 Argon |
| FrontierMath, tier 4 | 24.4% | 78.0% | Gemini 4 Argon |
| ProofBench | 56.0% | 99.0% | Gemini 4 Argon |
| LMArena Text: math | Not measured | 1536 | Only Gemini 4 Argon measured |
| LMArena Text: mathematical work | Not measured | 1557 | Only Gemini 4 Argon measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LegalBench (Vals AI) | 77.7% | 88.3% | Gemini 4 Argon |
| CorpFin (Vals AI) | 61.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| TaxEval (Vals AI) | 70.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MedCode (Vals AI) | 41.4% | 58.8% | Gemini 4 Argon |
| SimpleQA Verified | 33.6% | 76.0% | Gemini 4 Argon |
| LMArena Text: science | Not measured | 1548 | Only Gemini 4 Argon measured |
| LMArena Text: medicine and healthcare | Not measured | 1555 | Only Gemini 4 Argon measured |
| LMArena Text: legal and government | Not measured | 1548 | Only Gemini 4 Argon measured |
| LMArena Text: business and finance | Not measured | 1525 | Only Gemini 4 Argon measured |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | 1315 | Gemini 4 Argon |
| Design Arena: UI components | 1235 | 1331 | Gemini 4 Argon |
| Design Arena: game dev | 1208 | 1375 | Gemini 4 Argon |
| Design Arena: data viz | 1180 | 1336 | Gemini 4 Argon |
| Design Arena: 3D | 1209 | 1389 | Gemini 4 Argon |
| Design Arena: all code categories | 1230 | 1329 | Gemini 4 Argon |
| 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 |
| LiveBench design | Not measured | 73.7% | Only Gemini 4 Argon measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | Leader |
|---|---|---|---|
| Vals Index | Not measured | 69.2% | Only Gemini 4 Argon measured |
| LiveBench data analysis | Not measured | 85.2% | Only Gemini 4 Argon measured |
| Public Benefits Bench (Vals AI) | Not measured | 69.8% | Only Gemini 4 Argon measured |
| SAGE (Vals AI) | Not measured | 53.6% | Only Gemini 4 Argon measured |
| MedScribe (Vals AI) | 80.4% | 87.4% | Gemini 4 Argon |
| Long context reasoning (AA-LCR) | 79.7% | 79.7% | Tie |
| DTBench | 90.9% | 97.6% | Gemini 4 Argon |
| LMCA | 41.7% | 63.7% | Gemini 4 Argon |
| Furniture assembly | Not measured | 72.5% | Only Gemini 4 Argon measured |
| LMArena Text | Not measured | 1532 | Only Gemini 4 Argon measured |
| LMArena Text: instruction following | Not measured | 1534 | Only Gemini 4 Argon measured |
| LMArena Text: creative writing | Not measured | 1527 | Only Gemini 4 Argon measured |
| LMArena Text: English | Not measured | 1538 | Only Gemini 4 Argon measured |
| LMArena Text: non-English | Not measured | 1522 | Only Gemini 4 Argon measured |
| LMArena Text: Chinese | Not measured | 1611 | Only Gemini 4 Argon measured |
| LMArena Text: Spanish | Not measured | 1503 | Only Gemini 4 Argon measured |
| LMArena Text: Russian | Not measured | 1534 | Only Gemini 4 Argon measured |
| LMArena Text: multi-turn | Not measured | 1556 | Only Gemini 4 Argon measured |
| LMArena Text: longer queries | Not measured | 1547 | Only Gemini 4 Argon measured |
| LMArena Text: writing and language | Not measured | 1529 | Only Gemini 4 Argon measured |
| LMArena Text: entertainment and media | Not measured | 1527 | Only Gemini 4 Argon measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Gemini 4 Argon | 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 4 Argon |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | July 31, 2026 | October 13, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.14 | $2.00 |
| Output $/Mtok | $0.28 | $10.00 |
| Coding index | 51.8 | 81.0 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | $0.01 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Gemini 4 Argon for coding?
Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731. Pick DeepSeek V4 Flash 0731 for output tokens 35.7x cheaper ($0.28 vs $10.00 per million) and work measured by Terminal-Bench 2.1 (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Flash 0731 or Gemini 4 Argon?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. Cost per solved task is known for DeepSeek V4 Flash 0731 only.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Gemini 4 Argon?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Gemini 4 Argon comparison based on?
41 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 4 Argon's on 5. Where only one model has a result, the page says so instead of naming a winner.