GPT-5.4 Nano vs GPT-5.6 Terra
GPT-5.6 Terra leads GPT-5.4 Nano on coding, 63.9 to 44.8 on the Vibe Coding Index, and GPT-5.4 Nano costs 9.6x less per output token ($1.25 vs $12.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.
GPT-5.4 Nano or GPT-5.6 Terra: which to pick
Pick GPT-5.6 Terra for coding: it scores 63.9 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano.
Pick GPT-5.4 Nano for output tokens 9.6x cheaper ($1.25 vs $12.00 per million) and a lower cost per solved task ($0.14 against $0.42).
- Shared results
- 82
- GPT-5.4 Nano only
- 3
- GPT-5.6 Terra only
- 47
- 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
GPT-5.6 Terra
GPT-5.6 Terra scores 63.9 against 44.8.
2 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.6 Terra
GPT-5.6 Terra leads, 42.1 against 20.7.
Same board, both measured
Agentic work
AA Agentic Index
GPT-5.6 Terra
GPT-5.6 Terra leads, 43.2 against 16.0.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.6 Terra
GPT-5.6 Terra leads, 90.9% against 77.5%.
Same board, both measured
Math
AIME
No call
Only GPT-5.4 Nano has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
GPT-5.6 Terra
GPT-5.6 Terra leads, 86.7% against 77.2%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.6 Terra has a Design Arena: websites result, 1268.
Directional only
Long documents
Listed context window
GPT-5.6 Terra
GPT-5.6 Terra takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.4 Nano
GPT-5.4 Nano $0.0008, GPT-5.6 Terra $0.0080 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.4 Nano
GPT-5.4 Nano $0.14, GPT-5.6 Terra $0.42.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.4 Nano 44.8 from 2 benchmarks, GPT-5.6 Terra 63.9 from 6 benchmarks.
- Widest category
- Math, 33.7 points apart on average over 6 shared benchmarks.
- Widest single gap
- ARC-AGI-2: GPT-5.4 Nano 5.7% against GPT-5.6 Terra 83.9%, 78.2 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Nano $1.25 against GPT-5.6 Terra $12.00 per million output tokens, 9.6x apart.
- Context window
- GPT-5.4 Nano takes 400K tokens, GPT-5.6 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 | GPT-5.4 Nano | Bars | GPT-5.6 Terra | Ties |
|---|---|---|---|---|
| Coding | 0 | 12 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 6 | ||
| Reasoning | 0 | 15 | ||
| Math | 0 | 6 | ||
| Knowledge | 0 | 11 | ||
| General | 1 | 29 | ||
| All shared boards | 1 | 81 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 86.2% | Only GPT-5.6 Terra measured |
| LMArena WebDev | Not measured | 1522 | Only GPT-5.6 Terra measured |
| AA Coding Index | 56.1 | 76.7 | GPT-5.6 Terra |
| LiveCodeBench (Vals AI) | 84.0% | 85.9% | GPT-5.6 Terra |
| SWE-bench Verified (Vals AI) | 69.8% | 95.4% | GPT-5.6 Terra |
| Terminal-Bench 4 (Vals AI) | Not measured | 22.7% | Only GPT-5.6 Terra measured |
| Vibe Code Bench (Vals AI) | 26.1% | 74.6% | GPT-5.6 Terra |
| Code migration (Vals AI) | 14.5% | 47.8% | GPT-5.6 Terra |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only GPT-5.6 Terra measured |
| IOI (Vals AI) | Not measured | 87.6% | Only GPT-5.6 Terra measured |
| Terminal-Bench 2.1 (Vals AI) | 41.6% | 77.5% | GPT-5.6 Terra |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 14.8% | Only GPT-5.6 Terra measured |
| SkillsBench (Vals AI) | Not measured | 58.9% | Only GPT-5.6 Terra measured |
| CyberBench (Vals AI) | Not measured | 72.1% | Only GPT-5.6 Terra measured |
| SciCode | 47.2% | 55.0% | GPT-5.6 Terra |
| Terminal-Bench Hard (Artificial Analysis run) | 42.4% | 62.9% | GPT-5.6 Terra |
| FrontierCode | Not measured | 41.3% | Only GPT-5.6 Terra measured |
| WeirdML | 49.2% | 78.3% | GPT-5.6 Terra |
| ALE-Bench | 1004.5 | 1951.4 | GPT-5.6 Terra |
| LMArena Text: coding | 1404 | 1485 | GPT-5.6 Terra |
| LMArena Text: software and IT | 1402 | 1482 | GPT-5.6 Terra |
| LMArena WebDev: React | Not measured | 1513 | Only GPT-5.6 Terra measured |
| LMArena WebDev: HTML | Not measured | 1526 | Only GPT-5.6 Terra measured |
| LMArena WebDev: from an image | Not measured | 1541 | Only GPT-5.6 Terra measured |
| SciCode | Not measured | 10.8% | Only GPT-5.6 Terra measured |
| SWE-Bench Pro V2 | Not measured | 92.4% | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.7 | 42.1 | GPT-5.6 Terra |
| Epoch Capabilities Index | 146.0 | 160.1 | GPT-5.6 Terra |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| AA Agentic Index | 16.0 | 43.2 | GPT-5.6 Terra |
| Design Arena: agents building web apps | Not measured | 1120 | Only GPT-5.6 Terra measured |
| Design Arena: agents building full-stack apps | Not measured | 1061 | Only GPT-5.6 Terra measured |
| Design Arena: agents building mobile apps | Not measured | 1110 | Only GPT-5.6 Terra measured |
| Design Arena: agents building Android apps | Not measured | 1060 | Only GPT-5.6 Terra measured |
| Design Arena: agents building games | Not measured | 1083 | Only GPT-5.6 Terra measured |
| Design Arena: HTML slides | Not measured | 1047 | Only GPT-5.6 Terra measured |
| Design Arena: PowerPoint slides | Not measured | 1104 | Only GPT-5.6 Terra measured |
| LiveBench research | Not measured | 60.4% | Only GPT-5.6 Terra measured |
| LiveBench browser | Not measured | 84.0% | Only GPT-5.6 Terra measured |
| LiveBench long agentic | Not measured | 48.4% | Only GPT-5.6 Terra measured |
| SREBench (Vals AI) | Not measured | 9.5% | Only GPT-5.6 Terra measured |
| Finance Agent (Vals AI) | 38.2% | 54.4% | GPT-5.6 Terra |
| Tax Agent Bench (Vals AI) | 5.0% | 30.0% | GPT-5.6 Terra |
| Legal Research Bench (Vals AI) | 6.3% | 41.4% | GPT-5.6 Terra |
| Excel Modeling Benchmark (Vals AI) | 44.8% | 66.2% | GPT-5.6 Terra |
| Terminal-Bench-Science (Vals AI) | Not measured | 10.0% | Only GPT-5.6 Terra measured |
| τ²-Bench Telecom | 76.0% | 86.3% | GPT-5.6 Terra |
| APEX-Agents | Not measured | 58.2% | Only GPT-5.6 Terra measured |
| BALROG | Not measured | 53.2% | Only GPT-5.6 Terra measured |
| Vending-Bench 2 | Not measured | $7,343 | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index015
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| GPQA Diamond | 77.5% | 90.9% | GPT-5.6 Terra |
| LiveBench reasoning | Not measured | 90.6% | Only GPT-5.6 Terra measured |
| MMMU Pro (Vals AI) | 73.6% | 86.5% | GPT-5.6 Terra |
| GPQA Diamond (Artificial Analysis run) | 81.7% | 92.5% | GPT-5.6 Terra |
| Humanity's Last Exam (Artificial Analysis run) | 28.3% | 42.9% | GPT-5.6 Terra |
| GPQA Diamond (Epoch AI run) | 78.5% | 93.3% | GPT-5.6 Terra |
| ARC-AGI | 51.5% | 96.5% | GPT-5.6 Terra |
| ARC-AGI-2 | 5.7% | 83.9% | GPT-5.6 Terra |
| SimpleBench | Not measured | 48.9% | Only GPT-5.6 Terra measured |
| Chess puzzles | 45.0% | 47.0% | GPT-5.6 Terra |
| Mystery game puzzles | 9.0% | 35.0% | GPT-5.6 Terra |
| LMArena Text: hard prompts | 1381 | 1469 | GPT-5.6 Terra |
| LMArena Text: expert | 1396 | 1496 | GPT-5.6 Terra |
| LMArena Text: hard prompts in English | 1387 | 1465 | GPT-5.6 Terra |
| LMArena Vision: diagrams | 1210 | 1295 | GPT-5.6 Terra |
| LMArena Vision: homework | 1225 | 1312 | GPT-5.6 Terra |
| Kagi LLM Benchmark | 39.7% | 51.3% | GPT-5.6 Terra |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only GPT-5.4 Nano measured |
| OTIS Mock AIME | 87.8% | 99.7% | GPT-5.6 Terra |
| FrontierMath, tiers 1 to 3 | 44.9% | 86.0% | GPT-5.6 Terra |
| FrontierMath, tier 4 | 12.2% | 70.7% | GPT-5.6 Terra |
| ProofBench | 5.0% | 74.0% | GPT-5.6 Terra |
| LMArena Text: math | 1405 | 1465 | GPT-5.6 Terra |
| LMArena Text: mathematical work | 1409 | 1478 | GPT-5.6 Terra |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| MMLU Pro | 77.2% | 86.7% | GPT-5.6 Terra |
| LegalBench (Vals AI) | 77.9% | 85.1% | GPT-5.6 Terra |
| CaseLaw (Vals AI) | 51.9% | Not measured | Only GPT-5.4 Nano measured |
| CorpFin (Vals AI) | 61.2% | 65.3% | GPT-5.6 Terra |
| TaxEval (Vals AI) | 67.4% | 76.2% | GPT-5.6 Terra |
| MortgageTax (Vals AI) | 59.1% | 67.3% | GPT-5.6 Terra |
| MedCode (Vals AI) | 41.0% | 43.4% | GPT-5.6 Terra |
| SimpleQA Verified | 11.7% | 43.2% | GPT-5.6 Terra |
| LMArena Text: science | 1374 | 1452 | GPT-5.6 Terra |
| LMArena Text: medicine and healthcare | 1369 | 1430 | GPT-5.6 Terra |
| LMArena Text: legal and government | 1368 | 1461 | GPT-5.6 Terra |
| LMArena Text: business and finance | 1366 | 1448 | GPT-5.6 Terra |
| FACTS Benchmark Suite | Not measured | 52.0% | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1268 | Only GPT-5.6 Terra measured |
| Design Arena: UI components | Not measured | 1256 | Only GPT-5.6 Terra measured |
| Design Arena: game dev | Not measured | 1229 | Only GPT-5.6 Terra measured |
| Design Arena: data viz | Not measured | 1240 | Only GPT-5.6 Terra measured |
| Design Arena: 3D | Not measured | 1134 | Only GPT-5.6 Terra measured |
| Design Arena: all code categories | Not measured | 1240 | Only GPT-5.6 Terra measured |
| Design Arena: SVG | Not measured | 1219 | Only GPT-5.6 Terra measured |
| Design Arena: ASCII art | Not measured | 1178 | Only GPT-5.6 Terra measured |
| LiveBench design | Not measured | 76.0% | Only GPT-5.6 Terra measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index129
| Benchmark | GPT-5.4 Nano | GPT-5.6 Terra | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 79.3% | Only GPT-5.6 Terra measured |
| Public Benefits Bench (Vals AI) | Not measured | 62.4% | Only GPT-5.6 Terra measured |
| SAGE (Vals AI) | 38.1% | 47.0% | GPT-5.6 Terra |
| MedScribe (Vals AI) | 77.1% | 82.9% | GPT-5.6 Terra |
| Vals Multimodal Index | 47.6% | 65.1% | GPT-5.6 Terra |
| IFBench | 75.9% | 71.2% | GPT-5.4 Nano |
| Long context reasoning (AA-LCR) | 76.7% | 83.0% | GPT-5.6 Terra |
| DTBench | 80.3% | 93.3% | GPT-5.6 Terra |
| LMCA | 36.9% | 54.9% | GPT-5.6 Terra |
| Surface Evolver Bench | Not measured | 83.8% | Only GPT-5.6 Terra measured |
| Furniture assembly | Not measured | 54.2% | Only GPT-5.6 Terra measured |
| LMArena Text | 1372 | 1448 | GPT-5.6 Terra |
| LMArena Text: instruction following | 1362 | 1456 | GPT-5.6 Terra |
| LMArena Text: creative writing | 1315 | 1413 | GPT-5.6 Terra |
| LMArena Vision | 1196 | 1271 | GPT-5.6 Terra |
| LMArena Text: English | 1381 | 1449 | GPT-5.6 Terra |
| LMArena Text: non-English | 1359 | 1441 | GPT-5.6 Terra |
| LMArena Text: Chinese | 1391 | 1514 | GPT-5.6 Terra |
| LMArena Text: German | 1368 | 1460 | GPT-5.6 Terra |
| LMArena Text: Japanese | 1343 | 1454 | GPT-5.6 Terra |
| LMArena Text: Korean | 1321 | 1427 | GPT-5.6 Terra |
| LMArena Text: French | 1395 | 1466 | GPT-5.6 Terra |
| LMArena Text: Spanish | 1371 | 1451 | GPT-5.6 Terra |
| LMArena Text: Russian | 1363 | 1452 | GPT-5.6 Terra |
| LMArena Text: Polish | 1366 | 1446 | GPT-5.6 Terra |
| LMArena Text: multi-turn | 1382 | 1453 | GPT-5.6 Terra |
| LMArena Text: longer queries | 1365 | 1454 | GPT-5.6 Terra |
| LMArena Text: writing and language | 1338 | 1431 | GPT-5.6 Terra |
| LMArena Text: entertainment and media | 1325 | 1418 | GPT-5.6 Terra |
| LMArena Vision: English | 1202 | 1272 | GPT-5.6 Terra |
| LMArena Vision: Chinese | 1232 | 1337 | GPT-5.6 Terra |
| LMArena Vision: reading text | 1204 | 1278 | GPT-5.6 Terra |
| LMArena Vision: humor | 1161 | 1236 | GPT-5.6 Terra |
| LMArena Vision: recognizing things | 1141 | Not measured | Only GPT-5.4 Nano measured |
| LMArena Vision: creative writing | 1159 | 1248 | GPT-5.6 Terra |
| LMArena Document | Not measured | 1472 | Only GPT-5.6 Terra measured |
| EQ-Bench 4 | Not measured | 1234 | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Nano | GPT-5.6 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
GPT-5.4 Nano costs less
Repository review
50K input + 3K output tokens
GPT-5.4 Nano costs less
Agent loop
200K input + 10K output tokens
GPT-5.4 Nano 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 | OpenAI GPT-5.4 Nano | OpenAI GPT-5.6 Terra |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | March 17, 2026 | July 9, 2026 |
| Context window | 400K | 1.05M |
| Input $/Mtok | $0.20 | $2.00 |
| Output $/Mtok | $1.25 | $12.00 |
| Coding index | 44.8 | 63.9 |
| Independent measurements behind it | 2 | 6 |
| Cost per solved task | $0.14 | $0.42 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Nano better than GPT-5.6 Terra for coding?
Pick GPT-5.6 Terra for coding: it scores 63.9 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano. Pick GPT-5.4 Nano for output tokens 9.6x cheaper ($1.25 vs $12.00 per million) and a lower cost per solved task ($0.14 against $0.42).
Which is cheaper, GPT-5.4 Nano or GPT-5.6 Terra?
GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; GPT-5.6 Terra costs $2.00 and $12.00. Per solved SWE-bench Verified task, GPT-5.4 Nano costs $0.14 and GPT-5.6 Terra $0.42.
Which has the bigger context window, GPT-5.4 Nano or GPT-5.6 Terra?
GPT-5.6 Terra, with 1.05M tokens against 400K.
How many benchmarks is the GPT-5.4 Nano vs GPT-5.6 Terra comparison based on?
82 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Nano's coding index rests on 2 independent benchmarks and GPT-5.6 Terra's on 6. Where only one model has a result, the page says so instead of naming a winner.