GPT-6.1 Sol vs GPT-6.1 Terra
GPT-6.1 Sol leads GPT-6.1 Terra on coding, 82.3 to 77.4 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; 35 benchmarks have a result for both.
GPT-6.1 Sol or GPT-6.1 Terra: which to pick
Pick GPT-6.1 Sol for coding: it scores 82.3 on the Vibe Coding Index against 77.4 for GPT-6.1 Terra.
Pick GPT-6.1 Terra for output tokens 2.0x cheaper ($5.00 vs $10.00 per million) and work measured by APEX-Agents or EBR-bench, where it leads.
- Shared results
- 35
- GPT-6.1 Sol only
- 71
- GPT-6.1 Terra only
- 1
- 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
GPT-6.1 Sol
GPT-6.1 Sol scores 82.3 against 77.4.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-6.1 Sol
GPT-6.1 Sol leads, 54.5 against 51.0.
Same board, both measured
Web design
Design Arena: websites
GPT-6.1 Sol
GPT-6.1 Sol leads, 1315 against 1283.
Same board, both measured
General
Vals Index
GPT-6.1 Sol
GPT-6.1 Sol leads, 63.9% against 60.5%.
Same board, both measured
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 Sol $0.0070, GPT-6.1 Terra $0.0035 per turn.
List prices
At a glance
- Coding index
- GPT-6.1 Sol 82.3 from 5 benchmarks, GPT-6.1 Terra 77.4 from 4 benchmarks.
- Widest category
- Knowledge, 16.6 points apart on average over 1 shared benchmark.
- Widest single gap
- EBR-bench: GPT-6.1 Sol 54.3% against GPT-6.1 Terra 78.1%, 23.8 points apart on a 0 to 100 scale.
- Output price
- GPT-6.1 Sol $10.00 against GPT-6.1 Terra $5.00 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 Sol | Bars | GPT-6.1 Terra | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 6 | 1 | ||
| Reasoning | 4 | 1 | ||
| Math | 2 | 0 | 1 tie | |
| Knowledge | 1 | 0 | ||
| Web design | 4 | 1 | ||
| General | 5 | 0 | ||
| All shared boards | 31 | 3 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| LiveBench coding | 96.0% | 94.3% | GPT-6.1 Sol |
| LMArena WebDev | 1751 | 1673 | GPT-6.1 Sol |
| Terminal-Bench 4 (Vals AI) | 55.0% | 49.5% | GPT-6.1 Sol |
| Vibe Code Bench (Vals AI) | 88.9% | 84.0% | GPT-6.1 Sol |
| Code migration (Vals AI) | 65.1% | Not measured | Only GPT-6.1 Sol measured |
| ProgramBench (Vals AI) | 3.0% | Not measured | Only GPT-6.1 Sol measured |
| IOI (Vals AI) | 96.9% | Not measured | Only GPT-6.1 Sol measured |
| SWE-bench Multimodal (Vals AI) | 43.5% | Not measured | Only GPT-6.1 Sol measured |
| CyberBench (Vals AI) | 39.3% | Not measured | Only GPT-6.1 Sol measured |
| SciCode | 55.8% | 55.1% | GPT-6.1 Sol |
| FrontierCode | 50.2% | Not measured | Only GPT-6.1 Sol measured |
| ALE-Bench | 2743.8 | 2608.8 | GPT-6.1 Sol |
| LMArena Text: coding | 1486 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: software and IT | 1481 | Not measured | Only GPT-6.1 Sol measured |
| LMArena WebDev: React | 1752 | 1657 | GPT-6.1 Sol |
| LMArena WebDev: HTML | 1796 | 1719 | GPT-6.1 Sol |
| LMArena WebDev: from an image | 1702 | Not measured | Only GPT-6.1 Sol measured |
| SciCode | 9.2% | Not measured | Only GPT-6.1 Sol measured |
| SWE-Bench Pro V2 | 96.1% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| AA Intelligence Index | 54.5 | 51.0 | GPT-6.1 Sol |
| Epoch Capabilities Index | 168.4 | Not measured | Only GPT-6.1 Sol measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1308 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: agents building mobile apps | 1234 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: spreadsheets | 1288 | Not measured | Only GPT-6.1 Sol measured |
| LiveBench research | 83.5% | 73.9% | GPT-6.1 Sol |
| LiveBench browser | 93.3% | 93.1% | GPT-6.1 Sol |
| LiveBench long agentic | 68.7% | 48.6% | GPT-6.1 Sol |
| SREBench (Vals AI) | 50.8% | Not measured | Only GPT-6.1 Sol measured |
| Finance Agent (Vals AI) | 52.0% | Not measured | Only GPT-6.1 Sol measured |
| Tax Agent Bench (Vals AI) | 21.8% | 15.2% | GPT-6.1 Sol |
| Legal Research Bench (Vals AI) | 38.5% | 26.0% | GPT-6.1 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | 6.3% | 1.7% | GPT-6.1 Sol |
| Excel Modeling Benchmark (Vals AI) | 70.8% | Not measured | Only GPT-6.1 Sol measured |
| BioMysteryBench (Vals AI) | 79.6% | Not measured | Only GPT-6.1 Sol measured |
| Terminal-Bench-Science (Vals AI) | 52.9% | Not measured | Only GPT-6.1 Sol measured |
| Vals Science Index | 59.6% | Not measured | Only GPT-6.1 Sol measured |
| Robo-bench (Vals AI) | 28.3% | Not measured | Only GPT-6.1 Sol measured |
| APEX-Agents | 60.0% | 68.3% | GPT-6.1 Terra |
| SpireClimb | 24.7% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| LiveBench reasoning | 92.6% | 88.7% | GPT-6.1 Sol |
| MysteryMechanism (Vals AI) | 46.4% | Not measured | Only GPT-6.1 Sol measured |
| Humanity's Last Exam (Artificial Analysis run) | 52.9% | 46.2% | GPT-6.1 Sol |
| GPQA Diamond (Epoch AI run) | 95.4% | 94.3% | GPT-6.1 Sol |
| ARC-AGI | 98.5% | Not measured | Only GPT-6.1 Sol measured |
| ARC-AGI-2 | 94.2% | Not measured | Only GPT-6.1 Sol measured |
| Chess puzzles | 68.0% | Not measured | Only GPT-6.1 Sol measured |
| Mystery game puzzles | 80.0% | 74.0% | GPT-6.1 Sol |
| EBR-bench | 54.3% | 78.1% | GPT-6.1 Terra |
| LMArena Text: hard prompts | 1467 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: expert | 1499 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: hard prompts in English | 1469 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: diagrams | 1306 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: homework | 1356 | Not measured | Only GPT-6.1 Sol 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 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 100.0% | Tie |
| FrontierMath, tiers 1 to 3 | 93.7% | 90.9% | GPT-6.1 Sol |
| FrontierMath, tier 4 | 100.0% | 92.7% | GPT-6.1 Sol |
| ProofBench | 99.0% | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: math | 1486 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: mathematical work | 1515 | Not measured | Only GPT-6.1 Sol measured |
| MathArena | 84.0% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 48.8% | Not measured | Only GPT-6.1 Sol measured |
| SimpleQA Verified | 73.9% | 57.3% | GPT-6.1 Sol |
| LMArena Text: science | 1448 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: medicine and healthcare | 1431 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: legal and government | 1474 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: business and finance | 1449 | Not measured | Only GPT-6.1 Sol measured |
| FACTS Benchmark Suite | 74.6% | Not measured | Only GPT-6.1 Sol measured |
| PRBench Finance | 46.2% | Not measured | Only GPT-6.1 Sol measured |
| PRBench Legal | 47.9% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| Design Arena: websites | 1315 | 1283 | GPT-6.1 Sol |
| Design Arena: UI components | 1344 | 1277 | GPT-6.1 Sol |
| Design Arena: game dev | 1407 | 1348 | GPT-6.1 Sol |
| Design Arena: data viz | 1287 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: 3D | 1437 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: all code categories | 1357 | 1295 | GPT-6.1 Sol |
| LiveBench design | 82.1% | 82.3% | GPT-6.1 Terra |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-6.1 Sol | GPT-6.1 Terra | Leader |
|---|---|---|---|
| Vals Index | 63.9% | 60.5% | GPT-6.1 Sol |
| LiveBench data analysis | 82.7% | 82.3% | GPT-6.1 Sol |
| Public Benefits Bench (Vals AI) | 59.3% | Not measured | Only GPT-6.1 Sol measured |
| SAGE (Vals AI) | 90.5% | Not measured | Only GPT-6.1 Sol measured |
| MedScribe (Vals AI) | 86.5% | Not measured | Only GPT-6.1 Sol measured |
| Long context reasoning (AA-LCR) | 84.0% | 82.7% | GPT-6.1 Sol |
| DTBench | 96.5% | Not measured | Only GPT-6.1 Sol measured |
| LMCA | 62.8% | Not measured | Only GPT-6.1 Sol measured |
| Furniture assembly | 80.0% | 79.2% | GPT-6.1 Sol |
| LMArena Text | 1446 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: instruction following | 1467 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: creative writing | 1425 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision | 1288 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: English | 1453 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: non-English | 1436 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Chinese | 1491 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Japanese | 1414 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Korean | 1440 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: French | 1464 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Spanish | 1442 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Russian | 1457 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: multi-turn | 1442 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: longer queries | 1463 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: writing and language | 1442 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: entertainment and media | 1428 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: English | 1274 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: reading text | 1289 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: creative writing | 1301 | Not measured | Only GPT-6.1 Sol measured |
| MultiChallenge | 82.0% | 74.2% | GPT-6.1 Sol |
| EQ-Bench 4 | 1272 | Not measured | Only GPT-6.1 Sol 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 Sol | 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
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 Sol | OpenAI GPT-6.1 Terra |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | September 29, 2026 | October 26, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $1.00 |
| Output $/Mtok | $10.00 | $5.00 |
| Coding index | 82.3 | 77.4 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6.1 Sol better than GPT-6.1 Terra for coding?
Pick GPT-6.1 Sol for coding: it scores 82.3 on the Vibe Coding Index against 77.4 for GPT-6.1 Terra. Pick GPT-6.1 Terra for output tokens 2.0x cheaper ($5.00 vs $10.00 per million) and work measured by APEX-Agents or EBR-bench, where it leads.
Which is cheaper, GPT-6.1 Sol or GPT-6.1 Terra?
GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6.1 Terra costs $1.00 and $5.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-6.1 Sol or GPT-6.1 Terra?
Neither: both take 1.05M tokens.
How many benchmarks is the GPT-6.1 Sol vs GPT-6.1 Terra comparison based on?
35 benchmarks have a result for both models as of October 29, 2026. GPT-6.1 Sol's coding index rests on 5 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.