DeepSeek V3.2 Exp vs GPT-5.4 Pro
DeepSeek V3.2 Exp costs 439.0x less per output token than GPT-5.4 Pro ($0.41 vs $180.00 per million). Updated October 21, 2026; 2 benchmarks have a result for both.
DeepSeek V3.2 Exp or GPT-5.4 Pro: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3.2 Exp for output tokens 439.0x cheaper ($0.41 vs $180.00 per million) and work measured by WeirdML or Epoch Capabilities Index, where it leads.
- Shared results
- 2
- DeepSeek V3.2 Exp only
- 57
- GPT-5.4 Pro only
- 8
- Like-for-like categories
- 2 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only DeepSeek V3.2 Exp has a AA Intelligence Index result, 16.6.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3.2 Exp has a Design Arena: websites result, 1179.
Directional only
Long documents
Listed context window
GPT-5.4 Pro
GPT-5.4 Pro takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2 Exp
DeepSeek V3.2 Exp $0.0005, GPT-5.4 Pro $0.120 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3.2 Exp not benchmarked, GPT-5.4 Pro not benchmarked.
- Widest category
- Intelligence, 18.3 points apart on average over 1 shared benchmark.
- Widest single gap
- Epoch Capabilities Index: DeepSeek V3.2 Exp 144.9 against GPT-5.4 Pro 159.6, 18.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 Exp $0.41 against GPT-5.4 Pro $180.00 per million output tokens, 439.0x apart.
- Context window
- DeepSeek V3.2 Exp takes 164K tokens, GPT-5.4 Pro 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 V3.2 Exp | Bars | GPT-5.4 Pro | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| Aider polyglot | 74.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena WebDev | 1272 | Not measured | Only DeepSeek V3.2 Exp measured |
| LiveCodeBench (Artificial Analysis run) | 78.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| WeirdML | 39.5% | 57.4% | GPT-5.4 Pro |
| LMArena Text: coding | 1438 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: software and IT | 1438 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena WebDev: HTML | 1281 | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.6 | Not measured | Only DeepSeek V3.2 Exp measured |
| Epoch Capabilities Index | 144.9 | 159.6 | GPT-5.4 Pro |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 33.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| TheAgentCompany | 42.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Berkeley Function Calling Leaderboard (BFCL) | 56.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 79.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Humanity's Last Exam (Artificial Analysis run) | 14.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| GPQA Diamond (Epoch AI run) | Not measured | 94.6% | Only GPT-5.4 Pro measured |
| ARC-AGI | Not measured | 94.5% | Only GPT-5.4 Pro measured |
| ARC-AGI-2 | Not measured | 83.3% | Only GPT-5.4 Pro measured |
| SimpleBench | Not measured | 74.1% | Only GPT-5.4 Pro measured |
| Chess puzzles | Not measured | 59.0% | Only GPT-5.4 Pro measured |
| LMArena Text: hard prompts | 1429 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: expert | 1422 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: hard prompts in English | 1444 | Not measured | Only DeepSeek V3.2 Exp measured |
| Kagi LLM Benchmark | 52.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| AA Math Index | 87.7 | Not measured | Only DeepSeek V3.2 Exp measured |
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| FrontierMath, tiers 1 to 3 | Not measured | 82.5% | Only GPT-5.4 Pro measured |
| FrontierMath, tier 4 | Not measured | 58.5% | Only GPT-5.4 Pro measured |
| LMArena Text: math | 1422 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: mathematical work | 1433 | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 85.0% | Not measured | Only DeepSeek V3.2 Exp measured |
| SimpleQA Verified | Not measured | 46.3% | Only GPT-5.4 Pro measured |
| LMArena Text: science | 1443 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: medicine and healthcare | 1468 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: legal and government | 1419 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: business and finance | 1412 | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1179 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: UI components | 1167 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: game dev | 1144 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: data viz | 1152 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: 3D | 1148 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: all code categories | 1171 | Not measured | Only DeepSeek V3.2 Exp measured |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index24 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | Leader |
|---|---|---|---|
| IFBench | 54.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| Long context reasoning (AA-LCR) | 72.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| DTBench | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMCA | 29.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| Fiction.LiveBench | 83.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench | 13.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench Life | 9.5% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text | 1425 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: instruction following | 1401 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: creative writing | 1404 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: English | 1441 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: non-English | 1404 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Chinese | 1461 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: German | 1440 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Japanese | 1331 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Korean | 1372 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: French | 1434 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Spanish | 1441 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Russian | 1412 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: Polish | 1435 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: multi-turn | 1422 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: longer queries | 1418 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: entertainment and media | 1407 | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | GPT-5.4 Pro | 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 V3.2 Exp costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 Exp costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2 Exp 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 V3.2 Exp | OpenAI GPT-5.4 Pro |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | September 29, 2025 | March 5, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.27 | $30.00 |
| Output $/Mtok | $0.41 | $180.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 Exp better than GPT-5.4 Pro for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for output tokens 439.0x cheaper ($0.41 vs $180.00 per million) and work measured by WeirdML or Epoch Capabilities Index, where it leads.
Which is cheaper, DeepSeek V3.2 Exp or GPT-5.4 Pro?
DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; GPT-5.4 Pro costs $30.00 and $180.00. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3.2 Exp or GPT-5.4 Pro?
GPT-5.4 Pro, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 Exp vs GPT-5.4 Pro comparison based on?
2 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and GPT-5.4 Pro's on 0. Where only one model has a result, the page says so instead of naming a winner.