DeepSeek V4 Flash 0731 vs Qwen3.7 Max
Qwen3.7 Max leads DeepSeek V4 Flash 0731 on coding, 54.1 to 51.8 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 11.2x less per output token ($0.396 vs $4.425 per million). Updated October 22, 2026; 44 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Qwen3.7 Max: which to pick
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731, though on 3 benchmarks against 4.
Pick DeepSeek V4 Flash 0731 for output tokens 11.2x cheaper ($0.396 vs $4.425 per million) and a lower cost per solved task ($0.01 against $4.69).
- Shared results
- 44
- DeepSeek V4 Flash 0731 only
- 11
- Qwen3.7 Max only
- 15
- 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
Qwen3.7 Max
Qwen3.7 Max scores 54.1 against 51.8.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 29.5.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 22.5.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.7 Max
Qwen3.7 Max leads, 90.2% against 89.9%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.7 Max
Qwen3.7 Max leads, 89.3% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
Qwen3.7 Max
Qwen3.7 Max leads, 1274 against 1237.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, Qwen3.7 Max $0.0037 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.01, Qwen3.7 Max $4.69.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Qwen3.7 Max 54.1 from 3 benchmarks.
- Widest category
- Math, 12.0 points apart on average over 4 shared benchmarks.
- Widest single gap
- ProofBench: DeepSeek V4 Flash 0731 56.0% against Qwen3.7 Max 26.0%, 30.0 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.396 against Qwen3.7 Max $4.425 per million output tokens, 11.2x apart.
- Context window
- DeepSeek V4 Flash 0731 takes 1.05M tokens, Qwen3.7 Max 1M.
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 | Qwen3.7 Max | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 4 | 1 | ||
| Reasoning | 3 | 4 | ||
| Math | 1 | 3 | ||
| Knowledge | 1 | 5 | ||
| Web design | 0 | 8 | ||
| General | 2 | 2 | ||
| All shared boards | 21 | 23 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1515 | Only Qwen3.7 Max measured |
| AA Coding Index | 69.1 | 66.0 | DeepSeek V4 Flash 0731 |
| LiveCodeBench (Vals AI) | 87.3% | 87.1% | DeepSeek V4 Flash 0731 |
| SWE-bench Verified (Vals AI) | 88.8% | 68.8% | 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% | 47.7% | DeepSeek V4 Flash 0731 |
| Code migration (Vals AI) | 38.6% | 13.1% | DeepSeek V4 Flash 0731 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | 61.0% | 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 |
| SciCode | 50.3% | 49.5% | DeepSeek V4 Flash 0731 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 50.8% | Only Qwen3.7 Max measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| WeirdML | 63.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 1306.1 | 1189.4 | DeepSeek V4 Flash 0731 |
| LMArena WebDev: React | Not measured | 1514 | Only Qwen3.7 Max measured |
| LMArena WebDev: HTML | Not measured | 1512 | Only Qwen3.7 Max measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 29.5 | DeepSeek V4 Flash 0731 |
| Epoch Capabilities Index | 154.8 | 154.0 | DeepSeek V4 Flash 0731 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | 22.5 | DeepSeek V4 Flash 0731 |
| Design Arena: agents building web apps | Not measured | 1208 | Only Qwen3.7 Max measured |
| Design Arena: agents building full-stack apps | Not measured | 1191 | Only Qwen3.7 Max measured |
| Design Arena: agents building mobile apps | Not measured | 1155 | Only Qwen3.7 Max measured |
| Design Arena: agents building Android apps | Not measured | 1159 | Only Qwen3.7 Max measured |
| Design Arena: agents building Godot games | Not measured | 1187 | Only Qwen3.7 Max measured |
| Design Arena: agents building games | Not measured | 1161 | Only Qwen3.7 Max measured |
| Design Arena: HTML slides | Not measured | 1108 | Only Qwen3.7 Max measured |
| Design Arena: PowerPoint slides | Not measured | 1171 | Only Qwen3.7 Max measured |
| Finance Agent (Vals AI) | 49.5% | 47.8% | DeepSeek V4 Flash 0731 |
| Tax Agent Bench (Vals AI) | 28.1% | 15.8% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 25.5% | DeepSeek V4 Flash 0731 |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 57.0% | Qwen3.7 Max |
| 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 | 94.7% | Only Qwen3.7 Max measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | 90.2% | Qwen3.7 Max |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 92.3% | Qwen3.7 Max |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 40.5% | Qwen3.7 Max |
| GPQA Diamond (Epoch AI run) | 91.0% | 90.9% | DeepSeek V4 Flash 0731 |
| ARC-AGI | 89.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI-2 | 61.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SimpleBench | 61.1% | 70.4% | Qwen3.7 Max |
| Chess puzzles | 32.0% | 26.0% | DeepSeek V4 Flash 0731 |
| Mystery game puzzles | 34.0% | 32.0% | DeepSeek V4 Flash 0731 |
| EBR-bench | Not measured | 9.5% | Only Qwen3.7 Max measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | 95.6% | Qwen3.7 Max |
| FrontierMath, tiers 1 to 3 | 57.5% | 64.6% | Qwen3.7 Max |
| FrontierMath, tier 4 | 24.4% | 34.1% | Qwen3.7 Max |
| ProofBench | 56.0% | 26.0% | DeepSeek V4 Flash 0731 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 89.3% | Qwen3.7 Max |
| LegalBench (Vals AI) | 77.7% | 84.9% | Qwen3.7 Max |
| CorpFin (Vals AI) | 61.9% | 63.7% | Qwen3.7 Max |
| TaxEval (Vals AI) | 70.7% | 75.3% | Qwen3.7 Max |
| MedCode (Vals AI) | 41.4% | 38.8% | DeepSeek V4 Flash 0731 |
| SimpleQA Verified | 33.6% | 55.8% | Qwen3.7 Max |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| Design Arena: websites | 1237 | 1274 | Qwen3.7 Max |
| Design Arena: UI components | 1233 | 1267 | Qwen3.7 Max |
| Design Arena: game dev | 1207 | 1264 | Qwen3.7 Max |
| Design Arena: data viz | 1180 | 1275 | Qwen3.7 Max |
| Design Arena: 3D | 1208 | 1265 | Qwen3.7 Max |
| Design Arena: all code categories | 1229 | 1275 | Qwen3.7 Max |
| Design Arena: SVG | 1184 | 1216 | Qwen3.7 Max |
| Design Arena: ASCII art | 1090 | 1211 | Qwen3.7 Max |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 80.4% | 79.4% | DeepSeek V4 Flash 0731 |
| IFBench | Not measured | 80.5% | Only Qwen3.7 Max measured |
| Long context reasoning (AA-LCR) | 79.7% | 79.0% | DeepSeek V4 Flash 0731 |
| DTBench | 90.9% | 92.3% | Qwen3.7 Max |
| LMCA | 41.7% | 44.0% | Qwen3.7 Max |
| Neither model has a result on the other 41 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.7 Max | 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 | Qwen3.7 Max |
|---|---|---|
| Maker | DeepSeek | Qwen |
| Weights | Open weights | No public weights listed |
| Released | July 31, 2026 | May 21, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $0.14 | $1.475 |
| Output $/Mtok | $0.396 | $4.425 |
| Coding index | 51.8 | 54.1 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | $0.01 | $4.69 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Qwen3.7 Max for coding?
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731, though on 3 benchmarks against 4. Pick DeepSeek V4 Flash 0731 for output tokens 11.2x cheaper ($0.396 vs $4.425 per million) and a lower cost per solved task ($0.01 against $4.69).
Which is cheaper, DeepSeek V4 Flash 0731 or Qwen3.7 Max?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.396 per million output tokens; Qwen3.7 Max costs $1.475 and $4.425. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and Qwen3.7 Max $4.69.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Qwen3.7 Max?
DeepSeek V4 Flash 0731, with 1.05M tokens against 1M.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Qwen3.7 Max comparison based on?
44 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Qwen3.7 Max's on 3. Where only one model has a result, the page says so instead of naming a winner.