DeepSeek V3 0324 vs GPT-4o (2024-08-06)
Updated October 21, 2026. 20 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 0324 for coding: it scores 42.0 on the Vibe Coding Index against 23.1 for GPT-4o (2024-08-06).
Pick GPT-4o (2024-08-06) when what matters is LegalBench (Vals AI) or TaxEval (Vals AI), where it leads.
- Shared results
- 20
- DeepSeek V3 0324 only
- 15
- GPT-4o (2024-08-06) only
- 38
- Like-for-like categories
- 7 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 0324
DeepSeek V3 0324 scores 42.0 against 23.1.
One benchmark behind each score
Intelligence
AA Intelligence Index
DeepSeek V3 0324
DeepSeek V3 0324 leads, 9.7 against 7.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V3 0324 has a AA Agentic Index result, 0.8.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V3 0324 has a GPQA Diamond result, 61.6%.
Directional only
Math
AIME
DeepSeek V3 0324
DeepSeek V3 0324 leads, 52.2% against 14.0%.
Same board, both measured
Knowledge
MMLU Pro
DeepSeek V3 0324
DeepSeek V3 0324 leads, 79.5% against 74.1%.
Same board, both measured
Long documents
Listed context window
DeepSeek V3 0324
DeepSeek V3 0324 takes 164K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3 0324
DeepSeek V3 0324 $0.0009, GPT-4o (2024-08-06) $0.0075 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3 0324 42.0 from 1 benchmark, GPT-4o (2024-08-06) 23.1 from 1 benchmark.
- Widest category
- Math, 21.3 points apart on average over 5 shared benchmarks.
- Widest single gap
- AIME: DeepSeek V3 0324 52.2% against GPT-4o (2024-08-06) 14.0%, 38.2 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 0324 $1.14 against GPT-4o (2024-08-06) $10.00 per million output tokens, 8.8x apart.
- Context window
- DeepSeek V3 0324 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 0324 | Bars | GPT-4o (2024-08-06) | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 5 | 0 | ||
| Knowledge | 2 | 3 | ||
| General | 1 | 1 | ||
| All shared boards | 16 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index20
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 23.1% | Only GPT-4o (2024-08-06) measured |
| SWE-bench Verified | 42.0% | Not measured | Only DeepSeek V3 0324 measured |
| SWE-bench Lite | Not measured | 21.7% | Only GPT-4o (2024-08-06) measured |
| AA Coding Index | 21.2 | Not measured | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Vals AI) | 65.5% | Not measured | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Artificial Analysis run) | 40.5% | 31.7% | DeepSeek V3 0324 |
| SciCode | 39.0% | Not measured | Only DeepSeek V3 0324 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 15.2% | 8.3% | DeepSeek V3 0324 |
| WeirdML | 36.1% | Not measured | Only DeepSeek V3 0324 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 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.7 | 7.7 | DeepSeek V3 0324 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only DeepSeek V3 0324 measured |
| τ²-Bench Telecom | 47.1% | 28.9% | DeepSeek V3 0324 |
| METR time horizons | 49.6% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| GPQA Diamond | 61.6% | Not measured | Only DeepSeek V3 0324 measured |
| MMMU Pro (Vals AI) | Not measured | 64.0% | Only GPT-4o (2024-08-06) measured |
| GPQA Diamond (Artificial Analysis run) | 65.5% | 52.1% | DeepSeek V3 0324 |
| Humanity's Last Exam (Artificial Analysis run) | 4.7% | 2.3% | DeepSeek V3 0324 |
| GPQA Diamond (Epoch AI run) | 67.6% | 49.2% | DeepSeek V3 0324 |
| SimpleBench | 27.2% | 17.8% | DeepSeek V3 0324 |
| 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 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AIME | 52.2% | 14.0% | DeepSeek V3 0324 |
| MATH 500 (Vals AI) | 88.6% | 75.2% | DeepSeek V3 0324 |
| MGSM (Vals AI) | 91.7% | 90.7% | DeepSeek V3 0324 |
| AA Math Index | 41.0 | Not measured | Only DeepSeek V3 0324 measured |
| AIME 2025 (Artificial Analysis run) | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| OTIS Mock AIME | 37.8% | 6.4% | DeepSeek V3 0324 |
| FrontierMath, tiers 1 to 3 | Not measured | 0.4% | Only GPT-4o (2024-08-06) measured |
| MATH level 5 | 75.5% | 53.3% | DeepSeek V3 0324 |
| 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 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| MMLU Pro | 79.5% | 74.1% | DeepSeek V3 0324 |
| LegalBench (Vals AI) | 77.7% | 80.1% | GPT-4o (2024-08-06) |
| CorpFin (Vals AI) | 54.7% | 39.4% | DeepSeek V3 0324 |
| TaxEval (Vals AI) | 71.1% | 71.1% | GPT-4o (2024-08-06) |
| MortgageTax (Vals AI) | Not measured | 61.0% | Only GPT-4o (2024-08-06) measured |
| MedQA (Vals AI) | 82.0% | 88.2% | GPT-4o (2024-08-06) |
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only DeepSeek V3 0324 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 4 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V3 0324 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| IFBench | 41.0% | 36.0% | DeepSeek V3 0324 |
| Long context reasoning (AA-LCR) | 40.7% | 41.0% | GPT-4o (2024-08-06) |
| DTBench | 64.8% | Not measured | Only DeepSeek V3 0324 measured |
| LMCA | 15.5% | Not measured | Only DeepSeek V3 0324 measured |
| Fiction.LiveBench | 50.0% | Not measured | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | 77.0% | Not measured | Only DeepSeek V3 0324 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 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | 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 0324 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 0324 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 0324 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 0324 | OpenAI GPT-4o (2024-08-06) |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | March 24, 2025 | August 6, 2024 |
| Context window | 164K | 128K |
| Input $/Mtok | $0.29 | $2.50 |
| Output $/Mtok | $1.14 | $10.00 |
| Coding index | 42.0 | 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 0324 better than GPT-4o (2024-08-06) for coding?
Pick DeepSeek V3 0324 for coding: it scores 42.0 on the Vibe Coding Index against 23.1 for GPT-4o (2024-08-06). Pick GPT-4o (2024-08-06) when what matters is LegalBench (Vals AI) or TaxEval (Vals AI), where it leads.
Which is cheaper, DeepSeek V3 0324 or GPT-4o (2024-08-06)?
DeepSeek V3 0324 costs $0.29 per million input tokens and $1.14 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 0324 or GPT-4o (2024-08-06)?
DeepSeek V3 0324, with 164K tokens against 128K.
How many benchmarks is the DeepSeek V3 0324 vs GPT-4o (2024-08-06) comparison based on?
20 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3 0324'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.