DeepSeek V3.1 Terminus vs GPT-5.4 Mini
GPT-5.4 Mini leads DeepSeek V3.1 Terminus on the Artificial Analysis Intelligence Index, 24.1 to 14.8, and DeepSeek V3.1 Terminus costs 4.4x less per output token ($1.0142 vs $4.50 per million). Updated October 21, 2026; 34 benchmarks have a result for both.
DeepSeek V3.1 Terminus or GPT-5.4 Mini: which to pick
Only GPT-5.4 Mini has a coding score, 35.8 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 4.4x cheaper ($1.0142 vs $4.50 per million) and work measured by LMArena Text: hard prompts or LMArena Text: hard prompts in English, where it leads.
- Shared results
- 34
- DeepSeek V3.1 Terminus only
- 11
- GPT-5.4 Mini only
- 55
- Like-for-like categories
- 7 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-5.4 Mini has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.4 Mini
GPT-5.4 Mini leads, 24.1 against 14.8.
Same board, both measured
Agentic work
AA Agentic Index
GPT-5.4 Mini
GPT-5.4 Mini leads, 17.9 against 6.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-5.4 Mini has a GPQA Diamond result, 83.1%.
Directional only
Math
AIME
No call
Only GPT-5.4 Mini has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.4 Mini has a MMLU Pro result, 84.5%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3.1 Terminus has a Design Arena: websites result, 1187.
Directional only
Long documents
Listed context window
GPT-5.4 Mini
GPT-5.4 Mini 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-5.4 Mini $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 Mini has the number, $0.70.
Directional only
At a glance
- Coding index
- DeepSeek V3.1 Terminus not benchmarked, GPT-5.4 Mini 35.8 from 5 benchmarks.
- Widest category
- Agentic work, 28.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: DeepSeek V3.1 Terminus 37.1% against GPT-5.4 Mini 83.3%, 46.2 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.1 Terminus $1.0142 against GPT-5.4 Mini $4.50 per million output tokens, 4.4x apart.
- Context window
- DeepSeek V3.1 Terminus takes 164K tokens, GPT-5.4 Mini 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-5.4 Mini | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 3 | 2 | ||
| Math | 0 | 1 | ||
| Knowledge | 3 | 1 | ||
| General | 10 | 5 | ||
| All shared boards | 16 | 18 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1397 | Only GPT-5.4 Mini measured |
| AA Coding Index | 43.5 | 56.1 | GPT-5.4 Mini |
| LiveCodeBench (Vals AI) | Not measured | 81.5% | Only GPT-5.4 Mini measured |
| SWE-bench Verified (Vals AI) | Not measured | 73.0% | Only GPT-5.4 Mini measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 2.5% | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | Not measured | 48.0% | Only GPT-5.4 Mini measured |
| Code migration (Vals AI) | Not measured | 12.9% | Only GPT-5.4 Mini measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only GPT-5.4 Mini measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 54.7% | Only GPT-5.4 Mini measured |
| LiveCodeBench (Artificial Analysis run) | 79.8% | Not measured | Only DeepSeek V3.1 Terminus measured |
| SciCode | 38.0% | 52.1% | GPT-5.4 Mini |
| Terminal-Bench Hard (Artificial Analysis run) | 31.8% | 52.3% | GPT-5.4 Mini |
| FrontierCode | Not measured | 27.0% | Only GPT-5.4 Mini measured |
| WeirdML | Not measured | 60.3% | Only GPT-5.4 Mini measured |
| ALE-Bench | 745.2 | 1188.6 | GPT-5.4 Mini |
| LMArena Text: coding | 1425 | 1438 | GPT-5.4 Mini |
| LMArena Text: software and IT | 1426 | 1436 | GPT-5.4 Mini |
| LMArena WebDev: React | Not measured | 1386 | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | Not measured | 1419 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.8 | 24.1 | GPT-5.4 Mini |
| Epoch Capabilities Index | Not measured | 148.7 | Only GPT-5.4 Mini measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 6.8 | 17.9 | GPT-5.4 Mini |
| Finance Agent (Vals AI) | Not measured | 45.4% | Only GPT-5.4 Mini measured |
| Tax Agent Bench (Vals AI) | Not measured | 8.8% | Only GPT-5.4 Mini measured |
| Legal Research Bench (Vals AI) | Not measured | 12.5% | Only GPT-5.4 Mini measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 45.4% | Only GPT-5.4 Mini measured |
| τ²-Bench Telecom | 37.1% | 83.3% | GPT-5.4 Mini |
| DeepResearch Bench | Not measured | 36.3% | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.1% | Only GPT-5.4 Mini measured |
| MMMU Pro (Vals AI) | Not measured | 79.3% | Only GPT-5.4 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 79.2% | 87.5% | GPT-5.4 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 16.4% | 28.1% | GPT-5.4 Mini |
| GPQA Diamond (Epoch AI run) | Not measured | 86.9% | Only GPT-5.4 Mini measured |
| ARC-AGI | Not measured | 63.7% | Only GPT-5.4 Mini measured |
| ARC-AGI-2 | Not measured | 18.9% | Only GPT-5.4 Mini measured |
| Chess puzzles | Not measured | 23.0% | Only GPT-5.4 Mini measured |
| Mystery game puzzles | Not measured | 11.0% | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts | 1426 | 1424 | DeepSeek V3.1 Terminus |
| LMArena Text: expert | Not measured | 1435 | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts in English | 1432 | 1420 | DeepSeek V3.1 Terminus |
| LMArena Vision: diagrams | Not measured | 1266 | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | Not measured | 1285 | Only GPT-5.4 Mini measured |
| Kagi LLM Benchmark | 57.4% | 37.9% | DeepSeek V3.1 Terminus |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only GPT-5.4 Mini measured |
| AA Math Index | 89.7 | Not measured | Only DeepSeek V3.1 Terminus measured |
| AIME 2025 (Artificial Analysis run) | 89.7% | Not measured | Only DeepSeek V3.1 Terminus measured |
| OTIS Mock AIME | Not measured | 88.9% | Only GPT-5.4 Mini measured |
| FrontierMath, tiers 1 to 3 | Not measured | 51.2% | Only GPT-5.4 Mini measured |
| FrontierMath, tier 4 | Not measured | 9.8% | Only GPT-5.4 Mini measured |
| ProofBench | Not measured | 21.0% | Only GPT-5.4 Mini measured |
| LMArena Text: math | 1402 | 1418 | GPT-5.4 Mini |
| LMArena Text: mathematical work | Not measured | 1429 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.5% | Only GPT-5.4 Mini measured |
| CaseLaw (Vals AI) | Not measured | 51.7% | Only GPT-5.4 Mini measured |
| CorpFin (Vals AI) | Not measured | 60.9% | Only GPT-5.4 Mini measured |
| TaxEval (Vals AI) | Not measured | 71.2% | Only GPT-5.4 Mini measured |
| MortgageTax (Vals AI) | Not measured | 63.5% | Only GPT-5.4 Mini measured |
| MMLU Pro (Artificial Analysis run) | 85.1% | Not measured | Only DeepSeek V3.1 Terminus measured |
| SimpleQA Verified | Not measured | 29.4% | Only GPT-5.4 Mini measured |
| LMArena Text: science | 1451 | 1417 | DeepSeek V3.1 Terminus |
| LMArena Text: medicine and healthcare | 1468 | 1395 | DeepSeek V3.1 Terminus |
| LMArena Text: legal and government | 1457 | 1414 | DeepSeek V3.1 Terminus |
| LMArena Text: business and finance | 1414 | 1418 | GPT-5.4 Mini |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1187 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: UI components | 1182 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: game dev | 1131 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: data viz | 1167 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: 3D | 1141 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: all code categories | 1175 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Design Arena: SVG | 1065 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index105
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 50.8% | Only GPT-5.4 Mini measured |
| Vals Multimodal Index | Not measured | 54.2% | Only GPT-5.4 Mini measured |
| IFBench | 57.0% | 73.3% | GPT-5.4 Mini |
| Long context reasoning (AA-LCR) | 69.3% | 77.0% | GPT-5.4 Mini |
| DTBench | 81.3% | 80.0% | DeepSeek V3.1 Terminus |
| LMCA | 28.6% | 40.8% | GPT-5.4 Mini |
| LMArena Text | 1419 | 1412 | DeepSeek V3.1 Terminus |
| LMArena Text: instruction following | 1404 | 1405 | GPT-5.4 Mini |
| LMArena Text: creative writing | 1403 | 1370 | DeepSeek V3.1 Terminus |
| LMArena Vision | Not measured | 1245 | Only GPT-5.4 Mini measured |
| LMArena Text: English | 1429 | 1412 | DeepSeek V3.1 Terminus |
| LMArena Text: non-English | 1408 | 1405 | DeepSeek V3.1 Terminus |
| LMArena Text: Chinese | Not measured | 1446 | Only GPT-5.4 Mini measured |
| LMArena Text: German | Not measured | 1408 | Only GPT-5.4 Mini measured |
| LMArena Text: Japanese | Not measured | 1375 | Only GPT-5.4 Mini measured |
| LMArena Text: Korean | Not measured | 1370 | Only GPT-5.4 Mini measured |
| LMArena Text: French | Not measured | 1441 | Only GPT-5.4 Mini measured |
| LMArena Text: Spanish | Not measured | 1405 | Only GPT-5.4 Mini measured |
| LMArena Text: Russian | 1435 | 1417 | DeepSeek V3.1 Terminus |
| LMArena Text: Polish | 1427 | 1415 | DeepSeek V3.1 Terminus |
| LMArena Text: multi-turn | 1411 | 1429 | GPT-5.4 Mini |
| LMArena Text: longer queries | 1422 | 1408 | DeepSeek V3.1 Terminus |
| LMArena Text: writing and language | 1409 | 1393 | DeepSeek V3.1 Terminus |
| LMArena Text: entertainment and media | 1391 | 1373 | DeepSeek V3.1 Terminus |
| LMArena Vision: English | Not measured | 1244 | Only GPT-5.4 Mini measured |
| LMArena Vision: Chinese | Not measured | 1286 | Only GPT-5.4 Mini measured |
| LMArena Vision: reading text | Not measured | 1253 | Only GPT-5.4 Mini measured |
| LMArena Vision: humor | Not measured | 1235 | Only GPT-5.4 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1218 | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | Not measured | 1222 | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.1 Terminus | GPT-5.4 Mini | 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-5.4 Mini |
|---|---|---|
| Maker | DeepSeek | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | September 22, 2025 | March 17, 2026 |
| Context window | 164K | 400K |
| Input $/Mtok | $0.3063 | $0.75 |
| Output $/Mtok | $1.0142 | $4.50 |
| Coding index | Not benchmarked | 35.8 |
| Independent measurements behind it | 0 | 5 |
| Cost per solved task | Not computable | $0.70 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.1 Terminus better than GPT-5.4 Mini for coding?
Only GPT-5.4 Mini has a coding score, 35.8 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 4.4x cheaper ($1.0142 vs $4.50 per million) and work measured by LMArena Text: hard prompts or LMArena Text: hard prompts in English, where it leads.
Which is cheaper, DeepSeek V3.1 Terminus or GPT-5.4 Mini?
DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Cost per solved task is known for GPT-5.4 Mini only.
Which has the bigger context window, DeepSeek V3.1 Terminus or GPT-5.4 Mini?
GPT-5.4 Mini, with 400K tokens against 164K.
How many benchmarks is the DeepSeek V3.1 Terminus vs GPT-5.4 Mini comparison based on?
34 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-5.4 Mini's on 5. Where only one model has a result, the page says so instead of naming a winner.