DeepSeek V3 vs GPT-5.4
Updated October 21, 2026. 11 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
DeepSeek V3 scores 70.2 and GPT-5.4 37.7 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking.
Pick DeepSeek V3 when output tokens cost 14.6x less, or when the benchmark that matters is Design Arena: 3D, where it leads; pick GPT-5.4 when the context window is larger, 1.05M against 164K tokens, or when what matters is GPQA Diamond (Epoch AI run) or OTIS Mock AIME, where it leads.
- Shared results
- 11
- DeepSeek V3 only
- 2
- GPT-5.4 only
- 98
- Like-for-like categories
- 4 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, four public coding benchmarks
No call
70.2 against 37.7, from different benchmarks with none in common.
Directional only
Intelligence
AA Intelligence Index
No call
Only GPT-5.4 has a AA Intelligence Index result, 39.0.
Directional only
Reasoning
GPQA Diamond
No call
Only GPT-5.4 has a GPQA Diamond result, 91.7%.
Directional only
Math
AIME
No call
Only GPT-5.4 has a AIME result, 96.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 has a MMLU Pro result, 87.5%.
Directional only
Web design
Design Arena: websites
GPT-5.4
GPT-5.4 leads, 1199 against 1120.
Same board, both measured
Long documents
Listed context window
GPT-5.4
GPT-5.4 takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3
DeepSeek V3 $0.0008, GPT-5.4 $0.010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 has the number, $1.02.
Directional only
At a glance
- Coding index
- DeepSeek V3 70.2 from 1 benchmark, GPT-5.4 37.7 from 1 benchmark.
- Widest category
- Math, 48.9 points apart on average over 1 shared benchmark.
- Widest single gap
- OTIS Mock AIME: DeepSeek V3 48.9% against GPT-5.4 97.8%, 48.9 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 $1.0287 against GPT-5.4 $15.00 per million output tokens, 14.6x apart.
- Context window
- DeepSeek V3 takes 164K tokens, GPT-5.4 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 | Bars | GPT-5.4 | Ties |
|---|---|---|---|---|
| Reasoning | 0 | 1 | ||
| Math | 0 | 1 | ||
| Web design | 1 | 6 | ||
| General | 0 | 2 | ||
| All shared boards | 1 | 10 |
CodingDirectional onlyFour of these boards feed the Vibe Coding Index21 boards, none shared
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| Aider polyglot | 70.2% | Not measured | Only DeepSeek V3 measured |
| SWE-bench Lite | 30.7% | Not measured | Only DeepSeek V3 measured |
| LMArena WebDev | Not measured | 1464 | Only GPT-5.4 measured |
| AA Coding Index | Not measured | 71.1 | Only GPT-5.4 measured |
| LiveCodeBench (Vals AI) | Not measured | 84.1% | Only GPT-5.4 measured |
| SWE-bench Verified (Vals AI) | Not measured | 78.2% | Only GPT-5.4 measured |
| Vibe Code Bench (Vals AI) | Not measured | 67.4% | Only GPT-5.4 measured |
| Code migration (Vals AI) | Not measured | 35.0% | Only GPT-5.4 measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only GPT-5.4 measured |
| SkillsBench (Vals AI) | Not measured | 51.7% | Only GPT-5.4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 57.6% | Only GPT-5.4 measured |
| Terminal-Bench | Not measured | 81.8% | Only GPT-5.4 measured |
| GSO-Bench | Not measured | 31.4% | Only GPT-5.4 measured |
| WeirdML | Not measured | 77.7% | Only GPT-5.4 measured |
| MirrorCode | Not measured | 15.6% | Only GPT-5.4 measured |
| ALE-Bench | Not measured | 1607.0 | Only GPT-5.4 measured |
| LMArena Text: coding | Not measured | 1496 | Only GPT-5.4 measured |
| LMArena Text: software and IT | Not measured | 1491 | Only GPT-5.4 measured |
| LMArena WebDev: React | Not measured | 1454 | Only GPT-5.4 measured |
| LMArena WebDev: HTML | Not measured | 1478 | Only GPT-5.4 measured |
| LMArena WebDev: from an image | Not measured | 1436 | Only GPT-5.4 measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 39.0 | Only GPT-5.4 measured |
| Epoch Capabilities Index | Not measured | 157.3 | Only GPT-5.4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1059 | Only GPT-5.4 measured |
| Design Arena: agents building full-stack apps | Not measured | 1017 | Only GPT-5.4 measured |
| Design Arena: agents building mobile apps | Not measured | 1087 | Only GPT-5.4 measured |
| Design Arena: agents building Android apps | Not measured | 1037 | Only GPT-5.4 measured |
| Design Arena: agents building Godot games | Not measured | 1135 | Only GPT-5.4 measured |
| τ²-Bench Telecom | Not measured | 87.1% | Only GPT-5.4 measured |
| APEX-Agents | Not measured | 52.4% | Only GPT-5.4 measured |
| METR time horizons | Not measured | 74.3% | Only GPT-5.4 measured |
| DeepResearch Bench | Not measured | 35.1% | Only GPT-5.4 measured |
| PostTrainBench | Not measured | 19.0% | Only GPT-5.4 measured |
| Vending-Bench 2 | Not measured | $6,144 | Only GPT-5.4 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 91.7% | Only GPT-5.4 measured |
| MMMU Pro (Vals AI) | Not measured | 87.5% | Only GPT-5.4 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 92.0% | Only GPT-5.4 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 43.7% | Only GPT-5.4 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | 93.3% | GPT-5.4 |
| ARC-AGI | Not measured | 93.7% | Only GPT-5.4 measured |
| ARC-AGI-2 | Not measured | 74.0% | Only GPT-5.4 measured |
| Chess puzzles | Not measured | 48.0% | Only GPT-5.4 measured |
| Mystery game puzzles | Not measured | 37.0% | Only GPT-5.4 measured |
| EBR-bench | Not measured | 25.4% | Only GPT-5.4 measured |
| LMArena Text: hard prompts | Not measured | 1485 | Only GPT-5.4 measured |
| LMArena Text: expert | Not measured | 1507 | Only GPT-5.4 measured |
| LMArena Text: hard prompts in English | Not measured | 1479 | Only GPT-5.4 measured |
| LMArena Vision: diagrams | Not measured | 1327 | Only GPT-5.4 measured |
| LMArena Vision: homework | Not measured | 1336 | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| AIME | Not measured | 96.7% | Only GPT-5.4 measured |
| OTIS Mock AIME | 48.9% | 97.8% | GPT-5.4 |
| FrontierMath, tiers 1 to 3 | Not measured | 78.6% | Only GPT-5.4 measured |
| FrontierMath, tier 4 | Not measured | 49.0% | Only GPT-5.4 measured |
| ProofBench | Not measured | 56.0% | Only GPT-5.4 measured |
| LMArena Text: math | Not measured | 1488 | Only GPT-5.4 measured |
| LMArena Text: mathematical work | Not measured | 1497 | Only GPT-5.4 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 87.5% | Only GPT-5.4 measured |
| LegalBench (Vals AI) | Not measured | 86.0% | Only GPT-5.4 measured |
| CaseLaw (Vals AI) | Not measured | 63.8% | Only GPT-5.4 measured |
| CorpFin (Vals AI) | Not measured | 65.3% | Only GPT-5.4 measured |
| TaxEval (Vals AI) | Not measured | 74.0% | Only GPT-5.4 measured |
| MortgageTax (Vals AI) | Not measured | 68.3% | Only GPT-5.4 measured |
| MedQA (Vals AI) | Not measured | 96.1% | Only GPT-5.4 measured |
| MedCode (Vals AI) | Not measured | 41.3% | Only GPT-5.4 measured |
| SimpleQA Verified | Not measured | 45.1% | Only GPT-5.4 measured |
| LMArena Text: science | Not measured | 1479 | Only GPT-5.4 measured |
| LMArena Text: medicine and healthcare | Not measured | 1458 | Only GPT-5.4 measured |
| LMArena Text: legal and government | Not measured | 1486 | Only GPT-5.4 measured |
| LMArena Text: business and finance | Not measured | 1474 | Only GPT-5.4 measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1120 | 1199 | GPT-5.4 |
| Design Arena: UI components | 1093 | 1215 | GPT-5.4 |
| Design Arena: game dev | 1054 | 1195 | GPT-5.4 |
| Design Arena: data viz | 1089 | 1196 | GPT-5.4 |
| Design Arena: 3D | 1087 | 1065 | DeepSeek V3 |
| Design Arena: all code categories | 1108 | 1180 | GPT-5.4 |
| Design Arena: SVG | 976 | 1141 | GPT-5.4 |
| Design Arena: ASCII art | Not measured | 1188 | Only GPT-5.4 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3 | GPT-5.4 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.3% | Only GPT-5.4 measured |
| MedScribe (Vals AI) | Not measured | 77.5% | Only GPT-5.4 measured |
| IFBench | Not measured | 73.9% | Only GPT-5.4 measured |
| Long context reasoning (AA-LCR) | Not measured | 82.0% | Only GPT-5.4 measured |
| DTBench | 62.7% | 94.4% | GPT-5.4 |
| LMCA | 15.2% | 52.0% | GPT-5.4 |
| CL-bench | Not measured | 27.9% | Only GPT-5.4 measured |
| Furniture assembly | Not measured | 37.5% | Only GPT-5.4 measured |
| CL-bench Life | Not measured | 21.7% | Only GPT-5.4 measured |
| LMArena Text | Not measured | 1469 | Only GPT-5.4 measured |
| LMArena Text: instruction following | Not measured | 1469 | Only GPT-5.4 measured |
| LMArena Text: creative writing | Not measured | 1439 | Only GPT-5.4 measured |
| LMArena Vision | Not measured | 1303 | Only GPT-5.4 measured |
| LMArena Text: English | Not measured | 1467 | Only GPT-5.4 measured |
| LMArena Text: non-English | Not measured | 1465 | Only GPT-5.4 measured |
| LMArena Text: Chinese | Not measured | 1520 | Only GPT-5.4 measured |
| LMArena Text: German | Not measured | 1472 | Only GPT-5.4 measured |
| LMArena Text: Japanese | Not measured | 1485 | Only GPT-5.4 measured |
| LMArena Text: Korean | Not measured | 1449 | Only GPT-5.4 measured |
| LMArena Text: French | Not measured | 1493 | Only GPT-5.4 measured |
| LMArena Text: Spanish | Not measured | 1452 | Only GPT-5.4 measured |
| LMArena Text: Russian | Not measured | 1480 | Only GPT-5.4 measured |
| LMArena Text: Polish | Not measured | 1472 | Only GPT-5.4 measured |
| LMArena Text: multi-turn | Not measured | 1482 | Only GPT-5.4 measured |
| LMArena Text: longer queries | Not measured | 1473 | Only GPT-5.4 measured |
| LMArena Text: writing and language | Not measured | 1458 | Only GPT-5.4 measured |
| LMArena Text: entertainment and media | Not measured | 1438 | Only GPT-5.4 measured |
| LMArena Vision: English | Not measured | 1301 | Only GPT-5.4 measured |
| LMArena Vision: Chinese | Not measured | 1354 | Only GPT-5.4 measured |
| LMArena Vision: reading text | Not measured | 1312 | Only GPT-5.4 measured |
| LMArena Vision: humor | Not measured | 1284 | Only GPT-5.4 measured |
| LMArena Vision: recognizing things | Not measured | 1251 | Only GPT-5.4 measured |
| LMArena Vision: creative writing | Not measured | 1283 | Only GPT-5.4 measured |
| LMArena Document | Not measured | 1471 | Only GPT-5.4 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 | GPT-5.4 | 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 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 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 | OpenAI GPT-5.4 |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | December 26, 2024 | March 5, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.2574 | $2.50 |
| Output $/Mtok | $1.0287 | $15.00 |
| Coding index | 70.2 | 37.7 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | $1.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 better than GPT-5.4 for coding?
DeepSeek V3 scores 70.2 and GPT-5.4 37.7 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking. Pick DeepSeek V3 when output tokens cost 14.6x less, or when the benchmark that matters is Design Arena: 3D, where it leads; pick GPT-5.4 when the context window is larger, 1.05M against 164K tokens, or when what matters is GPQA Diamond (Epoch AI run) or OTIS Mock AIME, where it leads.
Which is cheaper, DeepSeek V3 or GPT-5.4?
DeepSeek V3 costs $0.2574 per million input tokens and $1.0287 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Cost per solved task is known for GPT-5.4 only.
Which has the bigger context window, DeepSeek V3 or GPT-5.4?
GPT-5.4, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3 vs GPT-5.4 comparison based on?
11 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3's coding index rests on 1 independent benchmark and GPT-5.4's on 1. Where only one model has a result, the page says so instead of naming a winner.