DeepSeek V3.1 Terminus vs GPT-5.1
GPT-5.1 leads DeepSeek V3.1 Terminus on the Artificial Analysis Intelligence Index, 24.7 to 14.8, and DeepSeek V3.1 Terminus costs 9.9x less per output token ($1.0142 vs $10.00 per million). Updated October 21, 2026; 41 benchmarks have a result for both.
DeepSeek V3.1 Terminus or GPT-5.1: which to pick
Only GPT-5.1 has a coding score, 40.4 on the Vibe Coding Index; DeepSeek V3.1 Terminus has none, so the two cannot be ranked on coding.
Pick DeepSeek V3.1 Terminus for output tokens 9.9x cheaper ($1.0142 vs $10.00 per million) and work measured by LMArena Text: medicine and healthcare or Design Arena: UI components, where it leads.
- Shared results
- 41
- DeepSeek V3.1 Terminus only
- 4
- GPT-5.1 only
- 60
- 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
No call
Only GPT-5.1 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.1
GPT-5.1 leads, 24.7 against 14.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V3.1 Terminus has a AA Agentic Index result, 6.8.
Directional only
Reasoning
GPQA Diamond
No call
Only GPT-5.1 has a GPQA Diamond result, 86.6%.
Directional only
Math
AIME
No call
Only GPT-5.1 has a AIME result, 93.3%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.1 has a MMLU Pro result, 86.4%.
Directional only
Web design
Design Arena: websites
No call
Tied at 1187.
Same board, both measured
Long documents
Listed context window
GPT-5.1
GPT-5.1 takes 400K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus $0.0008, GPT-5.1 $0.0063 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.1 has the number, $1.02.
Directional only
At a glance
- Coding index
- DeepSeek V3.1 Terminus not benchmarked, GPT-5.1 40.4 from 3 benchmarks.
- Widest category
- Agentic work, 44.7 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: DeepSeek V3.1 Terminus 37.1% against GPT-5.1 81.9%, 44.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.1 Terminus $1.0142 against GPT-5.1 $10.00 per million output tokens, 9.9x apart.
- Context window
- DeepSeek V3.1 Terminus takes 164K tokens, GPT-5.1 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 V3.1 Terminus | Bars | GPT-5.1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 3 | ||
| Knowledge | 1 | 4 | ||
| Web design | 3 | 3 | 1 tie | |
| General | 0 | 15 | ||
| All shared boards | 4 | 36 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 66.0% | Only GPT-5.1 measured |
| LMArena WebDev | Not measured | 1396 | Only GPT-5.1 measured |
| AA Coding Index | 43.5 | 49.4 | GPT-5.1 |
| LiveCodeBench (Vals AI) | Not measured | 86.5% | Only GPT-5.1 measured |
| SWE-bench Verified (Vals AI) | Not measured | 69.8% | Only GPT-5.1 measured |
| Vibe Code Bench (Vals AI) | Not measured | 24.6% | Only GPT-5.1 measured |
| LiveCodeBench (Artificial Analysis run) | 79.8% | 86.8% | GPT-5.1 |
| SciCode | 38.0% | Not measured | Only DeepSeek V3.1 Terminus measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.8% | 45.5% | GPT-5.1 |
| Terminal-Bench | Not measured | 47.6% | Only GPT-5.1 measured |
| GSO-Bench | Not measured | 13.7% | Only GPT-5.1 measured |
| WeirdML | Not measured | 60.8% | Only GPT-5.1 measured |
| ALE-Bench | 745.2 | Not measured | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: coding | 1425 | 1453 | GPT-5.1 |
| LMArena Text: software and IT | 1426 | 1454 | GPT-5.1 |
| LMArena WebDev: React | Not measured | 1307 | Only GPT-5.1 measured |
| LMArena WebDev: HTML | Not measured | 1405 | Only GPT-5.1 measured |
| LMArena WebDev: from an image | Not measured | 1421 | Only GPT-5.1 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.8 | 24.7 | GPT-5.1 |
| Epoch Capabilities Index | Not measured | 149.8 | Only GPT-5.1 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| AA Agentic Index | 6.8 | Not measured | Only DeepSeek V3.1 Terminus measured |
| τ²-Bench Telecom | 37.1% | 81.9% | GPT-5.1 |
| DeepResearch Bench | Not measured | 42.8% | Only GPT-5.1 measured |
| Vending-Bench 2 | Not measured | $1,473 | Only GPT-5.1 measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 86.6% | Only GPT-5.1 measured |
| MMMU Pro (Vals AI) | Not measured | 83.2% | Only GPT-5.1 measured |
| GPQA Diamond (Artificial Analysis run) | 79.2% | 87.3% | GPT-5.1 |
| Humanity's Last Exam (Artificial Analysis run) | 16.4% | 28.5% | GPT-5.1 |
| GPQA Diamond (Epoch AI run) | Not measured | 87.6% | Only GPT-5.1 measured |
| ARC-AGI | Not measured | 72.8% | Only GPT-5.1 measured |
| ARC-AGI-2 | Not measured | 17.6% | Only GPT-5.1 measured |
| SimpleBench | Not measured | 53.2% | Only GPT-5.1 measured |
| Chess puzzles | Not measured | 42.0% | Only GPT-5.1 measured |
| Mystery game puzzles | Not measured | 19.0% | Only GPT-5.1 measured |
| VPCT | Not measured | 58.7% | Only GPT-5.1 measured |
| LMArena Text: hard prompts | 1426 | 1457 | GPT-5.1 |
| LMArena Text: expert | Not measured | 1470 | Only GPT-5.1 measured |
| LMArena Text: hard prompts in English | 1432 | 1462 | GPT-5.1 |
| LMArena Vision: diagrams | Not measured | 1264 | Only GPT-5.1 measured |
| LMArena Vision: homework | Not measured | 1272 | Only GPT-5.1 measured |
| Kagi LLM Benchmark | 57.4% | Not measured | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| AIME | Not measured | 93.3% | Only GPT-5.1 measured |
| MGSM (Vals AI) | Not measured | 93.0% | Only GPT-5.1 measured |
| AA Math Index | 89.7 | 94.0 | GPT-5.1 |
| AIME 2025 (Artificial Analysis run) | 89.7% | 94.0% | GPT-5.1 |
| OTIS Mock AIME | Not measured | 88.6% | Only GPT-5.1 measured |
| LMArena Text: math | 1402 | 1446 | GPT-5.1 |
| LMArena Text: mathematical work | Not measured | 1449 | Only GPT-5.1 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.4% | Only GPT-5.1 measured |
| LegalBench (Vals AI) | Not measured | 85.7% | Only GPT-5.1 measured |
| CaseLaw (Vals AI) | Not measured | 73.4% | Only GPT-5.1 measured |
| CorpFin (Vals AI) | Not measured | 63.8% | Only GPT-5.1 measured |
| TaxEval (Vals AI) | Not measured | 74.9% | Only GPT-5.1 measured |
| MortgageTax (Vals AI) | Not measured | 61.4% | Only GPT-5.1 measured |
| MedQA (Vals AI) | Not measured | 96.4% | Only GPT-5.1 measured |
| MedCode (Vals AI) | Not measured | 52.7% | Only GPT-5.1 measured |
| MMLU Pro (Artificial Analysis run) | 85.1% | 87.0% | GPT-5.1 |
| SimpleQA Verified | Not measured | 48.0% | Only GPT-5.1 measured |
| LMArena Text: science | 1451 | 1459 | GPT-5.1 |
| LMArena Text: medicine and healthcare | 1468 | 1456 | DeepSeek V3.1 Terminus |
| LMArena Text: legal and government | 1457 | 1459 | GPT-5.1 |
| LMArena Text: business and finance | 1414 | 1431 | GPT-5.1 |
| FACTS Benchmark Suite | Not measured | 45.0% | Only GPT-5.1 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1187 | 1187 | Tie |
| Design Arena: UI components | 1182 | 1166 | DeepSeek V3.1 Terminus |
| Design Arena: game dev | 1131 | 1179 | GPT-5.1 |
| Design Arena: data viz | 1167 | 1204 | GPT-5.1 |
| Design Arena: 3D | 1141 | 1061 | DeepSeek V3.1 Terminus |
| Design Arena: all code categories | 1175 | 1171 | DeepSeek V3.1 Terminus |
| Design Arena: SVG | 1065 | 1149 | GPT-5.1 |
| Design Arena: ASCII art | Not measured | 1119 | Only GPT-5.1 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.2% | Only GPT-5.1 measured |
| MedScribe (Vals AI) | Not measured | 88.1% | Only GPT-5.1 measured |
| IFBench | 57.0% | 72.9% | GPT-5.1 |
| Long context reasoning (AA-LCR) | 69.3% | 80.0% | GPT-5.1 |
| DTBench | 81.3% | 90.1% | GPT-5.1 |
| LMCA | 28.6% | 43.9% | GPT-5.1 |
| CL-bench | Not measured | 23.7% | Only GPT-5.1 measured |
| CL-bench Life | Not measured | 17.3% | Only GPT-5.1 measured |
| LMArena Text | 1419 | 1443 | GPT-5.1 |
| LMArena Text: instruction following | 1404 | 1443 | GPT-5.1 |
| LMArena Text: creative writing | 1403 | 1427 | GPT-5.1 |
| LMArena Vision | Not measured | 1250 | Only GPT-5.1 measured |
| LMArena Text: English | 1429 | 1451 | GPT-5.1 |
| LMArena Text: non-English | 1408 | 1431 | GPT-5.1 |
| LMArena Text: Chinese | Not measured | 1495 | Only GPT-5.1 measured |
| LMArena Text: German | Not measured | 1438 | Only GPT-5.1 measured |
| LMArena Text: Japanese | Not measured | 1453 | Only GPT-5.1 measured |
| LMArena Text: Korean | Not measured | 1401 | Only GPT-5.1 measured |
| LMArena Text: French | Not measured | 1450 | Only GPT-5.1 measured |
| LMArena Text: Spanish | Not measured | 1433 | Only GPT-5.1 measured |
| LMArena Text: Russian | 1435 | 1435 | GPT-5.1 |
| LMArena Text: Polish | 1427 | 1440 | GPT-5.1 |
| LMArena Text: multi-turn | 1411 | 1450 | GPT-5.1 |
| LMArena Text: longer queries | 1422 | 1448 | GPT-5.1 |
| LMArena Text: writing and language | 1409 | 1428 | GPT-5.1 |
| LMArena Text: entertainment and media | 1391 | 1415 | GPT-5.1 |
| LMArena Vision: English | Not measured | 1252 | Only GPT-5.1 measured |
| LMArena Vision: Chinese | Not measured | 1270 | Only GPT-5.1 measured |
| LMArena Vision: reading text | Not measured | 1255 | Only GPT-5.1 measured |
| LMArena Vision: humor | Not measured | 1263 | Only GPT-5.1 measured |
| LMArena Vision: captioning | Not measured | 1252 | Only GPT-5.1 measured |
| LMArena Vision: recognizing things | Not measured | 1232 | Only GPT-5.1 measured |
| LMArena Vision: creative writing | Not measured | 1266 | Only GPT-5.1 measured |
| LMArena Document | Not measured | 1403 | Only GPT-5.1 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.1 | 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 V3.1 Terminus costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.1 Terminus costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.1 Terminus 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 V3.1 Terminus | OpenAI GPT-5.1 |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | September 22, 2025 | November 13, 2025 |
| Context window | 164K | 400K |
| Input $/Mtok | $0.3063 | $1.25 |
| Output $/Mtok | $1.0142 | $10.00 |
| Coding index | Not benchmarked | 40.4 |
| Independent measurements behind it | 0 | 3 |
| Cost per solved task | Not computable | $1.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.1 Terminus better than GPT-5.1 for coding?
Only GPT-5.1 has a coding score, 40.4 on the Vibe Coding Index; DeepSeek V3.1 Terminus has none, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for output tokens 9.9x cheaper ($1.0142 vs $10.00 per million) and work measured by LMArena Text: medicine and healthcare or Design Arena: UI components, where it leads.
Which is cheaper, DeepSeek V3.1 Terminus or GPT-5.1?
DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; GPT-5.1 costs $1.25 and $10.00. Cost per solved task is known for GPT-5.1 only.
Which has the bigger context window, DeepSeek V3.1 Terminus or GPT-5.1?
GPT-5.1, with 400K tokens against 164K.
How many benchmarks is the DeepSeek V3.1 Terminus vs GPT-5.1 comparison based on?
41 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and GPT-5.1's on 3. Where only one model has a result, the page says so instead of naming a winner.