GPT-6.1 Terra vs Step 5 Preview
GPT-6.1 Terra leads Step 5 Preview on coding, 77.4 to 61.2 on the Vibe Coding Index, and Step 5 Preview costs 1.9x less per output token ($2.70 vs $5.00 per million). Updated October 29, 2026; 18 benchmarks have a result for both.
GPT-6.1 Terra or Step 5 Preview: which to pick
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 61.2 for Step 5 Preview.
Pick Step 5 Preview for output tokens 1.9x cheaper ($2.70 vs $5.00 per million) and work measured by SciCode or Tax Agent Bench (Vals AI), where it leads.
- Shared results
- 18
- GPT-6.1 Terra only
- 18
- Step 5 Preview only
- 46
- Like-for-like categories
- 6 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 61.2.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-6.1 Terra
GPT-6.1 Terra leads, 51.0 against 28.5.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-6.1 Terra has a Design Arena: websites result, 1283.
Directional only
General
Vals Index
No call
Only GPT-6.1 Terra has a Vals Index result, 60.5%.
Directional only
Long documents
Listed context window
GPT-6.1 Terra
GPT-6.1 Terra takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 5 Preview
GPT-6.1 Terra $0.0035, Step 5 Preview $0.0024 per turn.
List prices
At a glance
- Coding index
- GPT-6.1 Terra 77.4 from 4 benchmarks, Step 5 Preview 61.2 from 4 benchmarks.
- Widest category
- Agentic work, 25.0 points apart on average over 5 shared benchmarks.
- Widest single gap
- LiveBench browser: GPT-6.1 Terra 93.1% against Step 5 Preview 24.8%, 68.3 points apart on a 0 to 100 scale.
- Output price
- GPT-6.1 Terra $5.00 against Step 5 Preview $2.70 per million output tokens, 1.9x apart.
- Context window
- GPT-6.1 Terra takes 1.05M tokens, Step 5 Preview 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-6.1 Terra | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 3 | 2 | ||
| Reasoning | 1 | 1 | ||
| Web design | 1 | 0 | ||
| General | 1 | 1 | ||
| All shared boards | 13 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | 94.3% | 85.6% | GPT-6.1 Terra |
| LMArena WebDev | 1673 | 1571 | GPT-6.1 Terra |
| Terminal-Bench 4 (Vals AI) | 49.5% | 31.8% | GPT-6.1 Terra |
| Vibe Code Bench (Vals AI) | 84.0% | 70.4% | GPT-6.1 Terra |
| Code migration (Vals AI) | Not measured | 39.0% | Only Step 5 Preview measured |
| IOI (Vals AI) | Not measured | 38.1% | Only Step 5 Preview measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Step 5 Preview measured |
| SciCode | 55.1% | 58.9% | Step 5 Preview |
| ALE-Bench | 2608.8 | Not measured | Only GPT-6.1 Terra measured |
| LMArena Text: coding | Not measured | 1482 | Only Step 5 Preview measured |
| LMArena Text: software and IT | Not measured | 1472 | Only Step 5 Preview measured |
| LMArena WebDev: React | 1657 | 1586 | GPT-6.1 Terra |
| LMArena WebDev: HTML | 1719 | 1555 | GPT-6.1 Terra |
| LMArena WebDev: from an image | Not measured | 1550 | Only Step 5 Preview measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 51.0 | 28.5 | GPT-6.1 Terra |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench research | 73.9% | 72.8% | GPT-6.1 Terra |
| LiveBench browser | 93.1% | 24.8% | GPT-6.1 Terra |
| LiveBench long agentic | 48.6% | 19.4% | GPT-6.1 Terra |
| SREBench (Vals AI) | Not measured | 0.4% | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | Not measured | 50.7% | Only Step 5 Preview measured |
| Tax Agent Bench (Vals AI) | 15.2% | 27.3% | Step 5 Preview |
| Legal Research Bench (Vals AI) | 26.0% | 40.4% | Step 5 Preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 1.7% | Not measured | Only GPT-6.1 Terra measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.1% | Only Step 5 Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 67.4% | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Step 5 Preview measured |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| APEX-Agents | 68.3% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.7% | 83.8% | GPT-6.1 Terra |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.2% | 46.5% | Step 5 Preview |
| GPQA Diamond (Epoch AI run) | 94.3% | Not measured | Only GPT-6.1 Terra measured |
| Mystery game puzzles | 74.0% | Not measured | Only GPT-6.1 Terra measured |
| EBR-bench | 78.1% | Not measured | Only GPT-6.1 Terra measured |
| LMArena Text: hard prompts | Not measured | 1463 | Only Step 5 Preview measured |
| LMArena Text: expert | Not measured | 1478 | Only Step 5 Preview measured |
| LMArena Text: hard prompts in English | Not measured | 1461 | Only Step 5 Preview measured |
| LMArena Vision: diagrams | Not measured | 1308 | Only Step 5 Preview measured |
| LMArena Vision: homework | Not measured | 1265 | Only Step 5 Preview measured |
| Humanity's Last Exam (Scale run) | 35.7% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only GPT-6.1 Terra measured |
| FrontierMath, tiers 1 to 3 | 90.9% | Not measured | Only GPT-6.1 Terra measured |
| FrontierMath, tier 4 | 92.7% | Not measured | Only GPT-6.1 Terra measured |
| ProofBench | Not measured | 42.0% | Only Step 5 Preview measured |
| LMArena Text: math | Not measured | 1457 | Only Step 5 Preview measured |
| LMArena Text: mathematical work | Not measured | 1462 | Only Step 5 Preview measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| SimpleQA Verified | 57.3% | Not measured | Only GPT-6.1 Terra measured |
| LMArena Text: science | Not measured | 1459 | Only Step 5 Preview measured |
| LMArena Text: medicine and healthcare | Not measured | 1439 | Only Step 5 Preview measured |
| LMArena Text: legal and government | Not measured | 1441 | Only Step 5 Preview measured |
| LMArena Text: business and finance | Not measured | 1443 | Only Step 5 Preview measured |
| Neither model has a result on the other 15 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1283 | Not measured | Only GPT-6.1 Terra measured |
| Design Arena: UI components | 1277 | Not measured | Only GPT-6.1 Terra measured |
| Design Arena: game dev | 1348 | Not measured | Only GPT-6.1 Terra measured |
| Design Arena: all code categories | 1295 | Not measured | Only GPT-6.1 Terra measured |
| LiveBench design | 82.3% | 76.9% | GPT-6.1 Terra |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-6.1 Terra | Step 5 Preview | Leader |
|---|---|---|---|
| Vals Index | 60.5% | Not measured | Only GPT-6.1 Terra measured |
| LiveBench data analysis | 82.3% | 63.5% | GPT-6.1 Terra |
| Public Benefits Bench (Vals AI) | Not measured | 58.1% | Only Step 5 Preview measured |
| Long context reasoning (AA-LCR) | 82.7% | 88.3% | Step 5 Preview |
| Furniture assembly | 79.2% | Not measured | Only GPT-6.1 Terra measured |
| LMArena Text | Not measured | 1443 | Only Step 5 Preview measured |
| LMArena Text: instruction following | Not measured | 1441 | Only Step 5 Preview measured |
| LMArena Text: creative writing | Not measured | 1413 | Only Step 5 Preview measured |
| LMArena Vision | Not measured | 1265 | Only Step 5 Preview measured |
| LMArena Text: English | Not measured | 1454 | Only Step 5 Preview measured |
| LMArena Text: non-English | Not measured | 1429 | Only Step 5 Preview measured |
| LMArena Text: Chinese | Not measured | 1502 | Only Step 5 Preview measured |
| LMArena Text: German | Not measured | 1454 | Only Step 5 Preview measured |
| LMArena Text: Japanese | Not measured | 1398 | Only Step 5 Preview measured |
| LMArena Text: Korean | Not measured | 1415 | Only Step 5 Preview measured |
| LMArena Text: French | Not measured | 1440 | Only Step 5 Preview measured |
| LMArena Text: Spanish | Not measured | 1444 | Only Step 5 Preview measured |
| LMArena Text: Russian | Not measured | 1431 | Only Step 5 Preview measured |
| LMArena Text: Polish | Not measured | 1390 | Only Step 5 Preview measured |
| LMArena Text: multi-turn | Not measured | 1437 | Only Step 5 Preview measured |
| LMArena Text: longer queries | Not measured | 1452 | Only Step 5 Preview measured |
| LMArena Text: writing and language | Not measured | 1427 | Only Step 5 Preview measured |
| LMArena Text: entertainment and media | Not measured | 1412 | Only Step 5 Preview measured |
| LMArena Vision: English | Not measured | 1290 | Only Step 5 Preview measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Step 5 Preview measured |
| MultiChallenge | 74.2% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6.1 Terra | Step 5 Preview | 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
Step 5 Preview costs less
Repository review
50K input + 3K output tokens
Step 5 Preview costs less
Agent loop
200K input + 10K output tokens
Step 5 Preview 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 | StepFun Step 5 Preview |
|---|---|---|
| Maker | OpenAI | StepFun |
| Weights | No public weights listed | Open weights |
| Released | October 26, 2026 | October 8, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.00 | $1.00 |
| Output $/Mtok | $5.00 | $2.70 |
| Coding index | 77.4 | 61.2 |
| 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 Step 5 Preview for coding?
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 61.2 for Step 5 Preview. Pick Step 5 Preview for output tokens 1.9x cheaper ($2.70 vs $5.00 per million) and work measured by SciCode or Tax Agent Bench (Vals AI), where it leads.
Which is cheaper, GPT-6.1 Terra or Step 5 Preview?
GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-6.1 Terra or Step 5 Preview?
GPT-6.1 Terra, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-6.1 Terra vs Step 5 Preview comparison based on?
18 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 Step 5 Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.