DeepSeek V3.2 vs GPT-5.1-Codex
DeepSeek V3.2 leads GPT-5.1-Codex on coding, 30.0 to 15.3 on the Vibe Coding Index, and DeepSeek V3.2 costs 11.4x less per output token ($0.88 vs $10.00 per million). Updated October 21, 2026; 22 benchmarks have a result for both.
DeepSeek V3.2 or GPT-5.1-Codex: which to pick
Pick DeepSeek V3.2 for coding: it scores 30.0 on the Vibe Coding Index against 15.3 for GPT-5.1-Codex.
Pick GPT-5.1-Codex for a lower cost per solved task ($0.892 against $0.99) and a larger context window (400K against 164K tokens).
- Shared results
- 22
- DeepSeek V3.2 only
- 53
- GPT-5.1-Codex only
- 4
- 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
DeepSeek V3.2
DeepSeek V3.2 scores 30.0 against 15.3.
3 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.1-Codex
GPT-5.1-Codex leads, 23.7 against 21.5.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V3.2 has a GPQA Diamond result, 80.3%.
Directional only
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3.2 has a MMLU Pro result, 84.9%.
Directional only
Web design
Design Arena: websites
DeepSeek V3.2
DeepSeek V3.2 leads, 1175 against 1162.
Same board, both measured
Long documents
Listed context window
GPT-5.1-Codex
GPT-5.1-Codex takes 400K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, GPT-5.1-Codex $0.0063 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.1-Codex
DeepSeek V3.2 $0.99, GPT-5.1-Codex $0.892.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, GPT-5.1-Codex 15.3 from 2 benchmarks.
- Widest category
- Agentic work, 7.6 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench: DeepSeek V3.2 39.6% against GPT-5.1-Codex 57.8%, 18.2 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against GPT-5.1-Codex $10.00 per million output tokens, 11.4x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, GPT-5.1-Codex 400K.
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 | Bars | GPT-5.1-Codex | Ties |
|---|---|---|---|---|
| Coding | 5 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 2 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 0 | ||
| Web design | 2 | 3 | ||
| General | 1 | 1 | ||
| All shared boards | 10 | 12 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index53
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | 66.0% | DeepSeek V3.2 |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | 1337 | DeepSeek V3.2 |
| AA Coding Index | 44.2 | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Vals AI) | 80.7% | 85.5% | GPT-5.1-Codex |
| SWE-bench Verified (Vals AI) | 67.6% | Not measured | Only DeepSeek V3.2 measured |
| Vibe Code Bench (Vals AI) | 5.1% | 13.1% | GPT-5.1-Codex |
| LiveCodeBench (Artificial Analysis run) | 86.2% | 84.9% | DeepSeek V3.2 |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | 34.8% | DeepSeek V3.2 |
| Terminal-Bench | 39.6% | 57.8% | GPT-5.1-Codex |
| ALE-Bench | Not measured | 1244.9 | Only GPT-5.1-Codex measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: HTML | 1371 | 1346 | DeepSeek V3.2 |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 23.7 | GPT-5.1-Codex |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1018 | Only GPT-5.1-Codex measured |
| Design Arena: agents building full-stack apps | Not measured | 1086 | Only GPT-5.1-Codex measured |
| Design Arena: agents building mobile apps | Not measured | 1191 | Only GPT-5.1-Codex measured |
| τ²-Bench Telecom | 90.6% | 83.0% | DeepSeek V3.2 |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | Not measured | Only DeepSeek V3.2 measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 86.0% | GPT-5.1-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 25.7% | GPT-5.1-Codex |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts | 1434 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | 95.7 | GPT-5.1-Codex |
| AIME 2025 (Artificial Analysis run) | 92.0% | 95.7% | GPT-5.1-Codex |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | Not measured | Only DeepSeek V3.2 measured |
| LegalBench (Vals AI) | 76.1% | Not measured | Only DeepSeek V3.2 measured |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | Not measured | Only DeepSeek V3.2 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only DeepSeek V3.2 measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | 86.0% | DeepSeek V3.2 |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1162 | DeepSeek V3.2 |
| Design Arena: UI components | 1149 | 1237 | GPT-5.1-Codex |
| Design Arena: game dev | 1132 | 1138 | GPT-5.1-Codex |
| Design Arena: data viz | 1158 | 1213 | GPT-5.1-Codex |
| Design Arena: 3D | 1133 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: all code categories | 1164 | 1152 | DeepSeek V3.2 |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1083 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V3.2 | GPT-5.1-Codex | Leader |
|---|---|---|---|
| IFBench | 60.7% | 70.0% | GPT-5.1-Codex |
| Long context reasoning (AA-LCR) | 73.3% | 69.3% | DeepSeek V3.2 |
| DTBench | 85.6% | Not measured | Only DeepSeek V3.2 measured |
| LMCA | 28.8% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 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 V3.2 | GPT-5.1-Codex | 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 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2 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 | OpenAI GPT-5.1-Codex |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | November 13, 2025 |
| Context window | 164K | 400K |
| Input $/Mtok | $0.29 | $1.25 |
| Output $/Mtok | $0.88 | $10.00 |
| Coding index | 30.0 | 15.3 |
| Independent measurements behind it | 3 | 2 |
| Cost per solved task | $0.99 | $0.892 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than GPT-5.1-Codex for coding?
Pick DeepSeek V3.2 for coding: it scores 30.0 on the Vibe Coding Index against 15.3 for GPT-5.1-Codex. Pick GPT-5.1-Codex for a lower cost per solved task ($0.892 against $0.99) and a larger context window (400K against 164K tokens).
Which is cheaper, DeepSeek V3.2 or GPT-5.1-Codex?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; GPT-5.1-Codex costs $1.25 and $10.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and GPT-5.1-Codex $0.892.
Which has the bigger context window, DeepSeek V3.2 or GPT-5.1-Codex?
GPT-5.1-Codex, with 400K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs GPT-5.1-Codex comparison based on?
22 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and GPT-5.1-Codex's on 2. Where only one model has a result, the page says so instead of naming a winner.