GPT-6.1 Terra vs GPT-6 Sol
GPT-6.1 Terra leads GPT-6 Sol on coding, 77.4 to 72.3 on the Vibe Coding Index, and GPT-6.1 Terra costs 2.0x less per output token ($5.00 vs $10.00 per million). Updated October 29, 2026; 25 benchmarks have a result for both.
GPT-6.1 Terra or GPT-6 Sol: which to pick
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 72.3 for GPT-6 Sol.
Pick GPT-6 Sol for work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 25
- GPT-6.1 Terra only
- 11
- GPT-6 Sol only
- 70
- 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-6.1 Terra
GPT-6.1 Terra scores 77.4 against 72.3.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only GPT-6.1 Terra has a AA Intelligence Index result, 51.0.
Directional only
Web design
Design Arena: websites
GPT-6 Sol
GPT-6 Sol leads, 1287 against 1283.
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
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-6.1 Terra
GPT-6.1 Terra $0.0035, GPT-6 Sol $0.0070 per turn.
List prices
At a glance
- Coding index
- GPT-6.1 Terra 77.4 from 4 benchmarks, GPT-6 Sol 72.3 from 4 benchmarks.
- Widest category
- General, 10.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- EBR-bench: GPT-6.1 Terra 78.1% against GPT-6 Sol 53.3%, 24.8 points apart on a 0 to 100 scale.
- Output price
- GPT-6.1 Terra $5.00 against GPT-6 Sol $10.00 per million output tokens, 2.0x apart.
- Context window
- Both take 1.05M tokens.
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-6.1 Terra | Bars | GPT-6 Sol | Ties |
|---|---|---|---|---|
| Coding | 3 | 4 | ||
| Agentic work | 2 | 1 | ||
| Reasoning | 3 | 1 | 1 tie | |
| Math | 2 | 0 | 1 tie | |
| Knowledge | 0 | 1 | ||
| Web design | 1 | 3 | ||
| General | 1 | 1 | ||
| All shared boards | 12 | 11 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index34
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| LiveBench coding | 94.3% | Not measured | Only GPT-6.1 Terra measured |
| LMArena WebDev | 1673 | 1678 | GPT-6 Sol |
| Terminal-Bench 4 (Vals AI) | 49.5% | 44.4% | GPT-6.1 Terra |
| Vibe Code Bench (Vals AI) | 84.0% | 87.8% | GPT-6 Sol |
| Code migration (Vals AI) | Not measured | 57.2% | Only GPT-6 Sol measured |
| ProgramBench (Vals AI) | Not measured | 2.0% | Only GPT-6 Sol measured |
| IOI (Vals AI) | Not measured | 82.6% | Only GPT-6 Sol measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 83.2% | Only GPT-6 Sol measured |
| CyberBench (Vals AI) | Not measured | 78.0% | Only GPT-6 Sol measured |
| SciCode | 55.1% | 57.6% | GPT-6 Sol |
| FrontierCode | Not measured | 49.3% | Only GPT-6 Sol measured |
| ALE-Bench | 2608.8 | 2462.0 | GPT-6.1 Terra |
| LMArena Text: coding | Not measured | 1447 | Only GPT-6 Sol measured |
| LMArena Text: software and IT | Not measured | 1431 | Only GPT-6 Sol measured |
| LMArena WebDev: React | 1657 | 1680 | GPT-6 Sol |
| LMArena WebDev: HTML | 1719 | 1680 | GPT-6.1 Terra |
| LMArena WebDev: from an image | Not measured | 1660 | Only GPT-6 Sol measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| AA Intelligence Index | 51.0 | Not measured | Only GPT-6.1 Terra measured |
| Epoch Capabilities Index | Not measured | 163.7 | Only GPT-6 Sol measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1234 | Only GPT-6 Sol measured |
| Design Arena: agents building full-stack apps | Not measured | 1237 | Only GPT-6 Sol measured |
| Design Arena: agents building mobile apps | Not measured | 1192 | Only GPT-6 Sol measured |
| LiveBench research | 73.9% | Not measured | Only GPT-6.1 Terra measured |
| LiveBench browser | 93.1% | Not measured | Only GPT-6.1 Terra measured |
| LiveBench long agentic | 48.6% | Not measured | Only GPT-6.1 Terra measured |
| SREBench (Vals AI) | Not measured | 30.5% | Only GPT-6 Sol measured |
| Finance Agent (Vals AI) | Not measured | 49.0% | Only GPT-6 Sol measured |
| Tax Agent Bench (Vals AI) | 15.2% | 15.0% | GPT-6.1 Terra |
| Legal Research Bench (Vals AI) | 26.0% | 28.9% | GPT-6 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | 1.7% | Not measured | Only GPT-6.1 Terra measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 71.5% | Only GPT-6 Sol measured |
| BioMysteryBench (Vals AI) | Not measured | 74.8% | Only GPT-6 Sol measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 30.0% | Only GPT-6 Sol measured |
| Vals Science Index | Not measured | 45.0% | Only GPT-6 Sol measured |
| APEX-Agents | 68.3% | 54.3% | GPT-6.1 Terra |
| SpireClimb | Not measured | 7.5% | Only GPT-6 Sol measured |
| Vending-Bench 2 | Not measured | $14,428 | Only GPT-6 Sol measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.7% | Not measured | Only GPT-6.1 Terra measured |
| MysteryMechanism (Vals AI) | Not measured | 30.2% | Only GPT-6 Sol measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.2% | 47.9% | GPT-6 Sol |
| GPQA Diamond (Epoch AI run) | 94.3% | 94.3% | Tie |
| ARC-AGI | Not measured | 95.5% | Only GPT-6 Sol measured |
| ARC-AGI-2 | Not measured | 89.6% | Only GPT-6 Sol measured |
| Chess puzzles | Not measured | 56.0% | Only GPT-6 Sol measured |
| Mystery game puzzles | 74.0% | 56.0% | GPT-6.1 Terra |
| EBR-bench | 78.1% | 53.3% | GPT-6.1 Terra |
| LMArena Text: hard prompts | Not measured | 1420 | Only GPT-6 Sol measured |
| LMArena Text: expert | Not measured | 1439 | Only GPT-6 Sol measured |
| LMArena Text: hard prompts in English | Not measured | 1417 | Only GPT-6 Sol measured |
| LMArena Vision: diagrams | Not measured | 1270 | Only GPT-6 Sol measured |
| LMArena Vision: homework | Not measured | 1286 | Only GPT-6 Sol measured |
| Humanity's Last Exam (Scale run) | 35.7% | 33.8% | GPT-6.1 Terra |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 100.0% | Tie |
| FrontierMath, tiers 1 to 3 | 90.9% | 89.8% | GPT-6.1 Terra |
| FrontierMath, tier 4 | 92.7% | 90.0% | GPT-6.1 Terra |
| ProofBench | Not measured | 83.0% | Only GPT-6 Sol measured |
| LMArena Text: math | Not measured | 1404 | Only GPT-6 Sol measured |
| LMArena Text: mathematical work | Not measured | 1422 | Only GPT-6 Sol measured |
| MathArena | Not measured | 79.9% | Only GPT-6 Sol measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 47.1% | Only GPT-6 Sol measured |
| SimpleQA Verified | 57.3% | 60.7% | GPT-6 Sol |
| LMArena Text: science | Not measured | 1390 | Only GPT-6 Sol measured |
| LMArena Text: medicine and healthcare | Not measured | 1367 | Only GPT-6 Sol measured |
| LMArena Text: legal and government | Not measured | 1393 | Only GPT-6 Sol measured |
| LMArena Text: business and finance | Not measured | 1381 | Only GPT-6 Sol measured |
| FACTS Benchmark Suite | Not measured | 68.4% | Only GPT-6 Sol measured |
| PRBench Legal | Not measured | 38.6% | Only GPT-6 Sol measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| Design Arena: websites | 1283 | 1287 | GPT-6 Sol |
| Design Arena: UI components | 1277 | 1290 | GPT-6 Sol |
| Design Arena: game dev | 1348 | 1310 | GPT-6.1 Terra |
| Design Arena: data viz | Not measured | 1270 | Only GPT-6 Sol measured |
| Design Arena: 3D | Not measured | 1310 | Only GPT-6 Sol measured |
| Design Arena: all code categories | 1295 | 1296 | GPT-6 Sol |
| Design Arena: SVG | Not measured | 1305 | Only GPT-6 Sol measured |
| Design Arena: ASCII art | Not measured | 1218 | Only GPT-6 Sol measured |
| LiveBench design | 82.3% | Not measured | Only GPT-6.1 Terra measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | Leader |
|---|---|---|---|
| Vals Index | 60.5% | Not measured | Only GPT-6.1 Terra measured |
| LiveBench data analysis | 82.3% | Not measured | Only GPT-6.1 Terra measured |
| Public Benefits Bench (Vals AI) | Not measured | 56.6% | Only GPT-6 Sol measured |
| MedScribe (Vals AI) | Not measured | 82.0% | Only GPT-6 Sol measured |
| Long context reasoning (AA-LCR) | 82.7% | 83.7% | GPT-6 Sol |
| DTBench | Not measured | 97.3% | Only GPT-6 Sol measured |
| LMCA | Not measured | 59.1% | Only GPT-6 Sol measured |
| Furniture assembly | 79.2% | 58.3% | GPT-6.1 Terra |
| LMArena Text | Not measured | 1397 | Only GPT-6 Sol measured |
| LMArena Text: instruction following | Not measured | 1411 | Only GPT-6 Sol measured |
| LMArena Text: creative writing | Not measured | 1378 | Only GPT-6 Sol measured |
| LMArena Vision | Not measured | 1240 | Only GPT-6 Sol measured |
| LMArena Text: English | Not measured | 1396 | Only GPT-6 Sol measured |
| LMArena Text: non-English | Not measured | 1388 | Only GPT-6 Sol measured |
| LMArena Text: Chinese | Not measured | 1414 | Only GPT-6 Sol measured |
| LMArena Text: German | Not measured | 1381 | Only GPT-6 Sol measured |
| LMArena Text: Japanese | Not measured | 1356 | Only GPT-6 Sol measured |
| LMArena Text: Korean | Not measured | 1334 | Only GPT-6 Sol measured |
| LMArena Text: French | Not measured | 1401 | Only GPT-6 Sol measured |
| LMArena Text: Spanish | Not measured | 1386 | Only GPT-6 Sol measured |
| LMArena Text: Russian | Not measured | 1405 | Only GPT-6 Sol measured |
| LMArena Text: Polish | Not measured | 1380 | Only GPT-6 Sol measured |
| LMArena Text: multi-turn | Not measured | 1411 | Only GPT-6 Sol measured |
| LMArena Text: longer queries | Not measured | 1416 | Only GPT-6 Sol measured |
| LMArena Text: writing and language | Not measured | 1388 | Only GPT-6 Sol measured |
| LMArena Text: entertainment and media | Not measured | 1372 | Only GPT-6 Sol measured |
| LMArena Vision: English | Not measured | 1229 | Only GPT-6 Sol measured |
| LMArena Vision: reading text | Not measured | 1258 | Only GPT-6 Sol measured |
| LMArena Vision: creative writing | Not measured | 1219 | Only GPT-6 Sol measured |
| MultiChallenge | 74.2% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6.1 Terra | GPT-6 Sol | 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-6.1 Terra costs less
Repository review
50K input + 3K output tokens
GPT-6.1 Terra costs less
Agent loop
200K input + 10K output tokens
GPT-6.1 Terra 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-6.1 Terra | OpenAI GPT-6 Sol |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 26, 2026 | September 22, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.00 | $2.00 |
| Output $/Mtok | $5.00 | $10.00 |
| Coding index | 77.4 | 72.3 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6.1 Terra better than GPT-6 Sol for coding?
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 72.3 for GPT-6 Sol. Pick GPT-6 Sol for work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, GPT-6.1 Terra or GPT-6 Sol?
GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-6 Sol costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-6.1 Terra or GPT-6 Sol?
Neither: both take 1.05M tokens.
How many benchmarks is the GPT-6.1 Terra vs GPT-6 Sol comparison based on?
25 benchmarks have a result for both models as of October 29, 2026. GPT-6.1 Terra's coding index rests on 4 independent benchmarks and GPT-6 Sol's on 4. Where only one model has a result, the page says so instead of naming a winner.