DeepSeek V3.2 vs GPT-6.1 Terra
GPT-6.1 Terra leads DeepSeek V3.2 on coding, 77.4 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 6.3x less per output token ($0.80 vs $5.00 per million). Updated October 29, 2026; 11 benchmarks have a result for both.
DeepSeek V3.2 or GPT-6.1 Terra: which to pick
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.
Pick DeepSeek V3.2 for output tokens 6.3x cheaper ($0.80 vs $5.00 per million).
- Shared results
- 11
- DeepSeek V3.2 only
- 63
- GPT-6.1 Terra only
- 25
- Like-for-like categories
- 5 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
GPT-6.1 Terra
GPT-6.1 Terra scores 77.4 against 30.0.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only GPT-6.1 Terra has a AA Intelligence Index result, 51.0.
Directional only
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
GPT-6.1 Terra
GPT-6.1 Terra leads, 1283 against 1174.
Same board, both measured
General
Vals Index
No call
Only GPT-6.1 Terra has a Vals Index result, 60.5%.
Directional only
Long documents
Listed context window
GPT-6.1 Terra
GPT-6.1 Terra takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, GPT-6.1 Terra $0.0035 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V3.2 has the number, $0.99.
Directional only
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, GPT-6.1 Terra 77.4 from 4 benchmarks.
- Widest category
- Coding, 50.8 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against GPT-6.1 Terra 84.0%, 78.9 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.80 against GPT-6.1 Terra $5.00 per million output tokens, 6.3x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, GPT-6.1 Terra 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 | Bars | GPT-6.1 Terra | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Web design | 0 | 4 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 11 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LiveBench coding | Not measured | 94.3% | Only GPT-6.1 Terra measured |
| LMArena WebDev | 1363 | 1673 | GPT-6.1 Terra |
| AA Coding Index | 44.2 | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Vals AI) | 80.7% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Verified (Vals AI) | 67.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 49.5% | Only GPT-6.1 Terra measured |
| Vibe Code Bench (Vals AI) | 5.1% | 84.0% | GPT-6.1 Terra |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 55.1% | Only GPT-6.1 Terra measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| ALE-Bench | Not measured | 2608.8 | Only GPT-6.1 Terra 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 | 1657 | GPT-6.1 Terra |
| LMArena WebDev: HTML | 1371 | 1719 | GPT-6.1 Terra |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 51.0 | Only GPT-6.1 Terra measured |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| LiveBench research | Not measured | 73.9% | Only GPT-6.1 Terra measured |
| LiveBench browser | Not measured | 93.1% | Only GPT-6.1 Terra measured |
| LiveBench long agentic | Not measured | 48.6% | Only GPT-6.1 Terra measured |
| Tax Agent Bench (Vals AI) | Not measured | 15.2% | Only GPT-6.1 Terra measured |
| Legal Research Bench (Vals AI) | Not measured | 26.0% | Only GPT-6.1 Terra measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 1.7% | Only GPT-6.1 Terra measured |
| τ²-Bench Telecom | 90.6% | Not measured | Only DeepSeek V3.2 measured |
| APEX-Agents | 21.3% | 68.3% | GPT-6.1 Terra |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | Not measured | Only DeepSeek V3.2 measured |
| LiveBench reasoning | Not measured | 88.7% | Only GPT-6.1 Terra measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | Not measured | Only DeepSeek V3.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 46.2% | GPT-6.1 Terra |
| GPQA Diamond (Epoch AI run) | Not measured | 94.3% | Only GPT-6.1 Terra measured |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| Mystery game puzzles | Not measured | 74.0% | Only GPT-6.1 Terra measured |
| EBR-bench | Not measured | 78.1% | Only GPT-6.1 Terra 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 |
| Humanity's Last Exam (Scale run) | Not measured | 35.7% | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| OTIS Mock AIME | Not measured | 100.0% | Only GPT-6.1 Terra measured |
| FrontierMath, tiers 1 to 3 | Not measured | 90.9% | Only GPT-6.1 Terra measured |
| FrontierMath, tier 4 | Not measured | 92.7% | Only GPT-6.1 Terra measured |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| MathArena | 15.5% | Not measured | Only DeepSeek V3.2 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 V3.2 | GPT-6.1 Terra | 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% | Not measured | Only DeepSeek V3.2 measured |
| SimpleQA Verified | Not measured | 57.3% | Only GPT-6.1 Terra measured |
| LMArena Text: science | 1445 | 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 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| Design Arena: websites | 1174 | 1283 | GPT-6.1 Terra |
| Design Arena: UI components | 1144 | 1277 | GPT-6.1 Terra |
| Design Arena: game dev | 1130 | 1348 | GPT-6.1 Terra |
| Design Arena: data viz | 1159 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: 3D | 1129 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: all code categories | 1162 | 1295 | GPT-6.1 Terra |
| Design Arena: SVG | 1030 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1080 | Not measured | Only DeepSeek V3.2 measured |
| LiveBench design | Not measured | 82.3% | Only GPT-6.1 Terra measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | GPT-6.1 Terra | Leader |
|---|---|---|---|
| Vals Index | Not measured | 60.5% | Only GPT-6.1 Terra measured |
| LiveBench data analysis | Not measured | 82.3% | Only GPT-6.1 Terra measured |
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | 82.7% | GPT-6.1 Terra |
| 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 |
| Furniture assembly | Not measured | 79.2% | Only GPT-6.1 Terra measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1424 | 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 | 1375 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1369 | 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 | 1423 | 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 |
| MultiChallenge | Not measured | 74.2% | Only GPT-6.1 Terra 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 V3.2 | GPT-6.1 Terra | 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-6.1 Terra |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | October 26, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.28 | $1.00 |
| Output $/Mtok | $0.80 | $5.00 |
| Coding index | 30.0 | 77.4 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.99 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than GPT-6.1 Terra for coding?
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 6.3x cheaper ($0.80 vs $5.00 per million).
Which is cheaper, DeepSeek V3.2 or GPT-6.1 Terra?
DeepSeek V3.2 costs $0.28 per million input tokens and $0.80 per million output tokens; GPT-6.1 Terra costs $1.00 and $5.00. Cost per solved task is known for DeepSeek V3.2 only.
Which has the bigger context window, DeepSeek V3.2 or GPT-6.1 Terra?
GPT-6.1 Terra, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs GPT-6.1 Terra comparison based on?
11 benchmarks have a result for both models as of October 29, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and GPT-6.1 Terra's on 4. Where only one model has a result, the page says so instead of naming a winner.