DeepSeek V4 Flash 0731 vs GPT-5.5
GPT-5.5 leads DeepSeek V4 Flash 0731 on coding, 71.3 to 51.8 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 107.1x less per output token ($0.28 vs $30.00 per million). Updated October 21, 2026; 50 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or GPT-5.5: which to pick
Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731.
Pick DeepSeek V4 Flash 0731 for output tokens 107.1x cheaper ($0.28 vs $30.00 per million) and a lower cost per solved task ($0.01 against $1.65).
- Shared results
- 50
- DeepSeek V4 Flash 0731 only
- 5
- GPT-5.5 only
- 84
- 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
GPT-5.5
GPT-5.5 scores 71.3 against 51.8.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.5
GPT-5.5 leads, 38.4 against 34.3.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 36.4.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.5
GPT-5.5 leads, 93.2% against 89.9%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.5
GPT-5.5 leads, 88.1% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
GPT-5.5
GPT-5.5 leads, 1256 against 1238.
Same board, both measured
Long documents
Listed context window
GPT-5.5
GPT-5.5 takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, GPT-5.5 $0.020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.01, GPT-5.5 $1.65.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, GPT-5.5 71.3 from 5 benchmarks.
- Widest category
- Math, 23.0 points apart on average over 4 shared benchmarks.
- Widest single gap
- FrontierMath, tier 4: DeepSeek V4 Flash 0731 24.4% against GPT-5.5 72.5%, 48.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against GPT-5.5 $30.00 per million output tokens, 107.1x apart.
- Context window
- DeepSeek V4 Flash 0731 takes 1.05M tokens, GPT-5.5 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 V4 Flash 0731 | Bars | GPT-5.5 | Ties |
|---|---|---|---|---|
| Coding | 3 | 9 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 3 | ||
| Reasoning | 1 | 8 | ||
| Math | 2 | 2 | ||
| Knowledge | 0 | 6 | ||
| Web design | 1 | 7 | ||
| General | 0 | 4 | ||
| All shared boards | 9 | 41 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index39
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 85.1% | Only GPT-5.5 measured |
| LMArena WebDev | Not measured | 1513 | Only GPT-5.5 measured |
| AA Coding Index | 69.1 | 74.9 | GPT-5.5 |
| LiveCodeBench (Vals AI) | 87.3% | 85.3% | DeepSeek V4 Flash 0731 |
| SWE-bench Verified (Vals AI) | 88.8% | 82.6% | 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% | 69.8% | DeepSeek V4 Flash 0731 |
| Code migration (Vals AI) | 38.6% | 45.2% | GPT-5.5 |
| ProgramBench (Vals AI) | 0.0% | 0.5% | GPT-5.5 |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | 76.4% | GPT-5.5 |
| SkillsBench (Vals AI) | 50.7% | 62.5% | GPT-5.5 |
| CyberBench (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SciCode | 50.3% | 56.1% | GPT-5.5 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 60.6% | Only GPT-5.5 measured |
| Terminal-Bench | Not measured | 84.7% | Only GPT-5.5 measured |
| FrontierCode | 18.8% | 43.0% | GPT-5.5 |
| GSO-Bench | Not measured | 40.2% | Only GPT-5.5 measured |
| WeirdML | 63.0% | 84.9% | GPT-5.5 |
| MirrorCode | Not measured | 10.0% | Only GPT-5.5 measured |
| ALE-Bench | 1306.1 | 1943.0 | GPT-5.5 |
| LMArena Text: coding | Not measured | 1494 | Only GPT-5.5 measured |
| LMArena Text: software and IT | Not measured | 1493 | Only GPT-5.5 measured |
| LMArena WebDev: React | Not measured | 1506 | Only GPT-5.5 measured |
| LMArena WebDev: HTML | Not measured | 1543 | Only GPT-5.5 measured |
| LMArena WebDev: from an image | Not measured | 1532 | Only GPT-5.5 measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 38.4 | GPT-5.5 |
| Epoch Capabilities Index | 154.8 | 159.7 | GPT-5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | 36.4 | DeepSeek V4 Flash 0731 |
| Design Arena: agents building web apps | Not measured | 1117 | Only GPT-5.5 measured |
| Design Arena: agents building full-stack apps | Not measured | 1089 | Only GPT-5.5 measured |
| Design Arena: agents building mobile apps | Not measured | 1143 | Only GPT-5.5 measured |
| Design Arena: agents building Android apps | Not measured | 1163 | Only GPT-5.5 measured |
| Design Arena: agents building Godot games | Not measured | 1173 | Only GPT-5.5 measured |
| Design Arena: agents building games | Not measured | 1179 | Only GPT-5.5 measured |
| Design Arena: HTML slides | Not measured | 1067 | Only GPT-5.5 measured |
| Design Arena: PowerPoint slides | Not measured | 1109 | Only GPT-5.5 measured |
| LiveBench research | Not measured | 61.6% | Only GPT-5.5 measured |
| LiveBench browser | Not measured | 48.0% | Only GPT-5.5 measured |
| LiveBench long agentic | Not measured | 44.6% | Only GPT-5.5 measured |
| SREBench (Vals AI) | Not measured | 3.8% | Only GPT-5.5 measured |
| Finance Agent (Vals AI) | 49.5% | 51.8% | GPT-5.5 |
| Tax Agent Bench (Vals AI) | 28.1% | 21.8% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 40.4% | GPT-5.5 |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 64.5% | GPT-5.5 |
| 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 |
| Time Horizon Index (Vals AI) | Not measured | 8.3% | Only GPT-5.5 measured |
| τ²-Bench Telecom | Not measured | 93.9% | Only GPT-5.5 measured |
| APEX-Agents | Not measured | 55.1% | Only GPT-5.5 measured |
| Remote Labor Index | Not measured | 6.3% | Only GPT-5.5 measured |
| OSWorld 2.0 | Not measured | 13.0% | Only GPT-5.5 measured |
| DeepResearch Bench | Not measured | 54.0% | Only GPT-5.5 measured |
| PostTrainBench | Not measured | 27.2% | Only GPT-5.5 measured |
| Vending-Bench 2 | Not measured | $7,524 | Only GPT-5.5 measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | 93.2% | GPT-5.5 |
| LiveBench reasoning | Not measured | 89.7% | Only GPT-5.5 measured |
| MMMU Pro (Vals AI) | Not measured | 88.3% | Only GPT-5.5 measured |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 93.5% | GPT-5.5 |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 45.8% | GPT-5.5 |
| GPQA Diamond (Epoch AI run) | 91.0% | 90.7% | DeepSeek V4 Flash 0731 |
| ARC-AGI | 89.0% | 95.0% | GPT-5.5 |
| ARC-AGI-2 | 61.4% | 85.0% | GPT-5.5 |
| SimpleBench | 61.1% | 69.0% | GPT-5.5 |
| Chess puzzles | 32.0% | 63.0% | GPT-5.5 |
| Mystery game puzzles | 34.0% | 56.0% | GPT-5.5 |
| EBR-bench | Not measured | 34.3% | Only GPT-5.5 measured |
| LMArena Text: hard prompts | Not measured | 1489 | Only GPT-5.5 measured |
| LMArena Text: expert | Not measured | 1507 | Only GPT-5.5 measured |
| LMArena Text: hard prompts in English | Not measured | 1483 | Only GPT-5.5 measured |
| LMArena Vision: diagrams | Not measured | 1325 | Only GPT-5.5 measured |
| LMArena Vision: homework | Not measured | 1332 | Only GPT-5.5 measured |
| Kagi LLM Benchmark | Not measured | 88.8% | Only GPT-5.5 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | 84.4% | DeepSeek V4 Flash 0731 |
| FrontierMath, tiers 1 to 3 | 57.5% | 85.3% | GPT-5.5 |
| FrontierMath, tier 4 | 24.4% | 72.5% | GPT-5.5 |
| ProofBench | 56.0% | 50.0% | DeepSeek V4 Flash 0731 |
| LMArena Text: math | Not measured | 1487 | Only GPT-5.5 measured |
| LMArena Text: mathematical work | Not measured | 1496 | Only GPT-5.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 88.1% | GPT-5.5 |
| LegalBench (Vals AI) | 77.7% | 86.5% | GPT-5.5 |
| CaseLaw (Vals AI) | Not measured | 66.2% | Only GPT-5.5 measured |
| CorpFin (Vals AI) | 61.9% | 68.4% | GPT-5.5 |
| TaxEval (Vals AI) | 70.7% | 75.0% | GPT-5.5 |
| MortgageTax (Vals AI) | Not measured | 68.8% | Only GPT-5.5 measured |
| MedCode (Vals AI) | 41.4% | 49.1% | GPT-5.5 |
| SimpleQA Verified | 33.6% | 63.0% | GPT-5.5 |
| LMArena Text: science | Not measured | 1485 | Only GPT-5.5 measured |
| LMArena Text: medicine and healthcare | Not measured | 1465 | Only GPT-5.5 measured |
| LMArena Text: legal and government | Not measured | 1491 | Only GPT-5.5 measured |
| LMArena Text: business and finance | Not measured | 1478 | Only GPT-5.5 measured |
| FACTS Benchmark Suite | Not measured | 66.7% | Only GPT-5.5 measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | 1256 | GPT-5.5 |
| Design Arena: UI components | 1235 | 1260 | GPT-5.5 |
| Design Arena: game dev | 1208 | 1294 | GPT-5.5 |
| Design Arena: data viz | 1180 | 1265 | GPT-5.5 |
| Design Arena: 3D | 1209 | 1198 | DeepSeek V4 Flash 0731 |
| Design Arena: all code categories | 1230 | 1260 | GPT-5.5 |
| Design Arena: SVG | 1185 | 1234 | GPT-5.5 |
| Design Arena: ASCII art | 1090 | 1255 | GPT-5.5 |
| LiveBench design | Not measured | 70.3% | Only GPT-5.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 81.6% | Only GPT-5.5 measured |
| Public Benefits Bench (Vals AI) | Not measured | 60.9% | Only GPT-5.5 measured |
| SAGE (Vals AI) | Not measured | 51.5% | Only GPT-5.5 measured |
| MedScribe (Vals AI) | 80.4% | 86.9% | GPT-5.5 |
| Vals Multimodal Index | Not measured | 68.1% | Only GPT-5.5 measured |
| IFBench | Not measured | 75.9% | Only GPT-5.5 measured |
| Long context reasoning (AA-LCR) | 79.7% | 84.3% | GPT-5.5 |
| DTBench | 90.9% | 96.0% | GPT-5.5 |
| LMCA | 41.7% | 54.3% | GPT-5.5 |
| Surface Evolver Bench | Not measured | 88.1% | Only GPT-5.5 measured |
| Furniture assembly | Not measured | 44.2% | Only GPT-5.5 measured |
| ExploitBench | Not measured | 47.4% | Only GPT-5.5 measured |
| CL-bench Life | Not measured | 22.2% | Only GPT-5.5 measured |
| LMArena Text | Not measured | 1471 | Only GPT-5.5 measured |
| LMArena Text: instruction following | Not measured | 1478 | Only GPT-5.5 measured |
| LMArena Text: creative writing | Not measured | 1455 | Only GPT-5.5 measured |
| LMArena Vision | Not measured | 1297 | Only GPT-5.5 measured |
| LMArena Text: English | Not measured | 1470 | Only GPT-5.5 measured |
| LMArena Text: non-English | Not measured | 1467 | Only GPT-5.5 measured |
| LMArena Text: Chinese | Not measured | 1534 | Only GPT-5.5 measured |
| LMArena Text: German | Not measured | 1480 | Only GPT-5.5 measured |
| LMArena Text: Japanese | Not measured | 1499 | Only GPT-5.5 measured |
| LMArena Text: Korean | Not measured | 1460 | Only GPT-5.5 measured |
| LMArena Text: French | Not measured | 1485 | Only GPT-5.5 measured |
| LMArena Text: Spanish | Not measured | 1468 | Only GPT-5.5 measured |
| LMArena Text: Russian | Not measured | 1473 | Only GPT-5.5 measured |
| LMArena Text: Polish | Not measured | 1465 | Only GPT-5.5 measured |
| LMArena Text: multi-turn | Not measured | 1476 | Only GPT-5.5 measured |
| LMArena Text: longer queries | Not measured | 1484 | Only GPT-5.5 measured |
| LMArena Text: writing and language | Not measured | 1466 | Only GPT-5.5 measured |
| LMArena Text: entertainment and media | Not measured | 1449 | Only GPT-5.5 measured |
| LMArena Vision: English | Not measured | 1292 | Only GPT-5.5 measured |
| LMArena Vision: Chinese | Not measured | 1360 | Only GPT-5.5 measured |
| LMArena Vision: reading text | Not measured | 1306 | Only GPT-5.5 measured |
| LMArena Vision: humor | Not measured | 1293 | Only GPT-5.5 measured |
| LMArena Vision: recognizing things | Not measured | 1231 | Only GPT-5.5 measured |
| LMArena Vision: creative writing | Not measured | 1301 | Only GPT-5.5 measured |
| LMArena Document | Not measured | 1486 | Only GPT-5.5 measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | GPT-5.5 | 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 | OpenAI GPT-5.5 |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | July 31, 2026 | April 24, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.14 | $5.00 |
| Output $/Mtok | $0.28 | $30.00 |
| Coding index | 51.8 | 71.3 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | $0.01 | $1.65 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than GPT-5.5 for coding?
Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731. Pick DeepSeek V4 Flash 0731 for output tokens 107.1x cheaper ($0.28 vs $30.00 per million) and a lower cost per solved task ($0.01 against $1.65).
Which is cheaper, DeepSeek V4 Flash 0731 or GPT-5.5?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and GPT-5.5 $1.65.
Which has the bigger context window, DeepSeek V4 Flash 0731 or GPT-5.5?
GPT-5.5, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4 Flash 0731 vs GPT-5.5 comparison based on?
50 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 GPT-5.5's on 5. Where only one model has a result, the page says so instead of naming a winner.