DeepSeek V3 vs GPT-4o (2024-08-06)
Updated October 21, 2026. 4 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 V3 for coding: it scores 70.2 on the Vibe Coding Index against 23.1 for GPT-4o (2024-08-06).
GPT-4o (2024-08-06) is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 4
- DeepSeek V3 only
- 9
- GPT-4o (2024-08-06) only
- 54
- Like-for-like categories
- 3 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
DeepSeek V3
DeepSeek V3 scores 70.2 against 23.1.
One benchmark behind each score
Intelligence
AA Intelligence Index
No call
Only GPT-4o (2024-08-06) has a AA Intelligence Index result, 7.7.
Directional only
Math
AIME
No call
Only GPT-4o (2024-08-06) has a AIME result, 14.0%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4o (2024-08-06) has a MMLU Pro result, 74.1%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3 has a Design Arena: websites result, 1120.
Directional only
Long documents
Listed context window
DeepSeek V3
DeepSeek V3 takes 164K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3
DeepSeek V3 $0.0008, GPT-4o (2024-08-06) $0.0075 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3 70.2 from 1 benchmark, GPT-4o (2024-08-06) 23.1 from 1 benchmark.
- Widest category
- Math, 42.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Aider polyglot: DeepSeek V3 70.2% against GPT-4o (2024-08-06) 23.1%, 47.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 $1.0287 against GPT-4o (2024-08-06) $10.00 per million output tokens, 9.7x apart.
- Context window
- DeepSeek V3 takes 164K tokens, GPT-4o (2024-08-06) 128K.
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-4o (2024-08-06) | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Reasoning | 1 | 0 | ||
| Math | 1 | 0 | ||
| All shared boards | 4 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index20
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Aider polyglot | 70.2% | 23.1% | DeepSeek V3 |
| SWE-bench Lite | 30.7% | 21.7% | DeepSeek V3 |
| LiveCodeBench (Artificial Analysis run) | Not measured | 31.7% | Only GPT-4o (2024-08-06) measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 8.3% | Only GPT-4o (2024-08-06) measured |
| LMArena Text: coding | Not measured | 1283 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: software and IT | Not measured | 1278 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 7.7 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 28.9% | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| MMMU Pro (Vals AI) | Not measured | 64.0% | Only GPT-4o (2024-08-06) measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 52.1% | Only GPT-4o (2024-08-06) measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 2.3% | Only GPT-4o (2024-08-06) measured |
| GPQA Diamond (Epoch AI run) | 71.2% | 49.2% | DeepSeek V3 |
| SimpleBench | Not measured | 17.8% | Only GPT-4o (2024-08-06) measured |
| Chess puzzles | Not measured | 6.0% | Only GPT-4o (2024-08-06) measured |
| LMArena Text: hard prompts | Not measured | 1264 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: expert | Not measured | 1241 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: hard prompts in English | Not measured | 1277 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AIME | Not measured | 14.0% | Only GPT-4o (2024-08-06) measured |
| MATH 500 (Vals AI) | Not measured | 75.2% | Only GPT-4o (2024-08-06) measured |
| MGSM (Vals AI) | Not measured | 90.7% | Only GPT-4o (2024-08-06) measured |
| OTIS Mock AIME | 48.9% | 6.4% | DeepSeek V3 |
| FrontierMath, tiers 1 to 3 | Not measured | 0.4% | Only GPT-4o (2024-08-06) measured |
| MATH level 5 | Not measured | 53.3% | Only GPT-4o (2024-08-06) measured |
| LMArena Text: math | Not measured | 1285 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: mathematical work | Not measured | 1283 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 74.1% | Only GPT-4o (2024-08-06) measured |
| LegalBench (Vals AI) | Not measured | 80.1% | Only GPT-4o (2024-08-06) measured |
| CorpFin (Vals AI) | Not measured | 39.4% | Only GPT-4o (2024-08-06) measured |
| TaxEval (Vals AI) | Not measured | 71.1% | Only GPT-4o (2024-08-06) measured |
| MortgageTax (Vals AI) | Not measured | 61.0% | Only GPT-4o (2024-08-06) measured |
| MedQA (Vals AI) | Not measured | 88.2% | Only GPT-4o (2024-08-06) measured |
| SimpleQA Verified | Not measured | 26.0% | Only GPT-4o (2024-08-06) measured |
| MMLU | Not measured | 84.3% | Only GPT-4o (2024-08-06) measured |
| LMArena Text: science | Not measured | 1274 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: medicine and healthcare | Not measured | 1252 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: legal and government | Not measured | 1275 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: business and finance | Not measured | 1232 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Design Arena: websites | 1120 | Not measured | Only DeepSeek V3 measured |
| Design Arena: UI components | 1093 | Not measured | Only DeepSeek V3 measured |
| Design Arena: game dev | 1054 | Not measured | Only DeepSeek V3 measured |
| Design Arena: data viz | 1089 | Not measured | Only DeepSeek V3 measured |
| Design Arena: 3D | 1087 | Not measured | Only DeepSeek V3 measured |
| Design Arena: all code categories | 1108 | Not measured | Only DeepSeek V3 measured |
| Design Arena: SVG | 976 | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| IFBench | Not measured | 36.0% | Only GPT-4o (2024-08-06) measured |
| Long context reasoning (AA-LCR) | Not measured | 41.0% | Only GPT-4o (2024-08-06) measured |
| DTBench | 62.7% | Not measured | Only DeepSeek V3 measured |
| LMCA | 15.2% | Not measured | Only DeepSeek V3 measured |
| LMArena Text | Not measured | 1283 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: instruction following | Not measured | 1267 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: creative writing | Not measured | 1274 | Only GPT-4o (2024-08-06) measured |
| LMArena Vision | Not measured | 1065 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: English | Not measured | 1297 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: non-English | Not measured | 1262 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: Chinese | Not measured | 1254 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: German | Not measured | 1257 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: Japanese | Not measured | 1234 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: Korean | Not measured | 1218 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: French | Not measured | 1263 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: Spanish | Not measured | 1269 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: Russian | Not measured | 1272 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: multi-turn | Not measured | 1279 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: longer queries | Not measured | 1283 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: writing and language | Not measured | 1290 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: entertainment and media | Not measured | 1267 | Only GPT-4o (2024-08-06) measured |
| LMArena Vision: English | Not measured | 1072 | Only GPT-4o (2024-08-06) measured |
| LMArena Vision: Chinese | Not measured | 1009 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 | GPT-4o (2024-08-06) | 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-4o (2024-08-06) |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | December 26, 2024 | August 6, 2024 |
| Context window | 164K | 128K |
| Input $/Mtok | $0.2574 | $2.50 |
| Output $/Mtok | $1.0287 | $10.00 |
| Coding index | 70.2 | 23.1 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 better than GPT-4o (2024-08-06) for coding?
Pick DeepSeek V3 for coding: it scores 70.2 on the Vibe Coding Index against 23.1 for GPT-4o (2024-08-06). GPT-4o (2024-08-06) is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, DeepSeek V3 or GPT-4o (2024-08-06)?
DeepSeek V3 costs $0.2574 per million input tokens and $1.0287 per million output tokens; GPT-4o (2024-08-06) costs $2.50 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3 or GPT-4o (2024-08-06)?
DeepSeek V3, with 164K tokens against 128K.
How many benchmarks is the DeepSeek V3 vs GPT-4o (2024-08-06) comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3's coding index rests on 1 independent benchmark and GPT-4o (2024-08-06)'s on 1. Where only one model has a result, the page says so instead of naming a winner.