GPT-6.1 Terra vs GPT-6.1 Sol and Opus 5.5
Measured by the CUELO maintainer
GPT-6.1 Terra was released on 2026-10-26. This study compared it with GPT-6.1 Sol and Opus 5.5 to decide which CUELO roles it should take. On coding, Terra finished large-sheet in 128 s with 199/200 hidden tests, but on mega-six it stopped after 4 of 6 packages (585/960, Sol 957/960) and reported the work incomplete. On image reading, Terra matched Opus on coordinates and box checks but got 138/153 small-text OCR items to Opus's 149/153.
Coding
How does GPT-6.1 Terra compare with GPT-6.1 Sol, both at high effort, on two large coding tasks under the same harness conditions?
Setup
- Runner: the omp CLI run non-interactively (
omp -p --no-session) with an isolation config, embedded omp core 18.13.0, reasoning effort high for both models, 90-minute cap. - Tools limited to
read,bash,edit,write,find,grep,evalandtodo, which blocks delegation (task) andask. Extension tools such asskimandcross_reviewstayed callable. large-sheet: build a spreadsheet formula engine (parser, evaluator, dependency graph, structural edits, CSV) from a spec in TypeScript + Bun, graded by 200 hidden tests after the run.mega-six: build six independent packages (spreadsheet, markdown, JSON schema, cron, semver, diff) from specs, graded by 960 hidden tests after the run.- One run per model per task, one after another, with the order alternated (Sol then Terra on one task, Terra then Sol on the other).
- Cost is token counts times catalogue prices per 1M tokens (Terra: input $1, output $5, cache read $0.05; Sol: input $2, output $10, cache read $0.10). The runs used a Codex subscription, so these are not billed amounts.
cross_review.large-sheet
Hidden tests passed (of 200)
Wall time
API-price cost
mega-six
Hidden tests passed (of 960)
Wall time
API-price cost
- Waiting for cross_review
Results
- On
large-sheetboth models were close to full marks: Terra 199/200 in 128 s, Sol 198/200 in 1,348 s. - On
mega-sixTerra implemented 4 of the 6 packages, stopped, and said in its final report that the work was incomplete (585/960). Sol passed 957/960. - Sol called
cross_reviewon its own and waited 533 s and 394 s for another model's review; without that wait its runs took 815 s and 724 s. Terra did not call it. Terra averaged about 6–7 s per model request, Sol about 22–24 s.
| Task · model | Passed | Time | Review wait | Requests | Seconds per request | Output tokens | Reasoning tokens | Cost |
|---|---|---|---|---|---|---|---|---|
| large-sheet · Terra | 199/200 | 128 s | 0 s | 18 | 6.4 | 10,318 | 427 | $0.146 |
| large-sheet · Sol | 198/200 | 1,348 s | 533 s | 33 | 24.1 | 34,286 | 9,636 | $0.756 |
| mega-six · Terra | 585/960 | 171 s | 0 s | 21 | 7.1 | 15,521 | 1,297 | $0.251 |
| mega-six · Sol | 957/960 | 1,118 s | 394 s | 32 | 21.9 | 45,066 | 7,936 | $1.057 |
Limits
- Each model ran each task once, so variance is unknown, and the maintainer cannot tell from this data whether Terra stopping early on
mega-sixis a tendency or chance. - The maintainer did not use an earlier Sol measurement from 2026-09-30 as a baseline because its runner and the omp core version had changed.
Image reading
Can GPT-6.1 Terra at low or high effort replace Opus 5.5 at low effort for image questions in the omp core?
Setup
- Same harness as a 2026-10-18 study: the omp core image-question path, with the answer key regenerated byte-identical.
- Four synthetic images (a game-style stats screen, the same screen with a deliberately wrong red box, a promotional banner and a small document table) and 8 question types.
- Opus 5.5 low (CUELO's current vision model), Terra low and Terra high, each run 3 times: 72 calls, 0 errors.
Small-text OCR correct (of 153)
Median latency
Results
- All three candidates got 27/27 coordinates and 12/12 box checks.
- On small-text OCR, Opus 5.5 low got 149/153 and both Terra settings 138/153. Most of Terra's misses were on the banner's small text (15/24, Opus 24/24).
- Terra gave the same OCR answers in all 3 runs, and its misreads were the same each time:
Lv.45read asLv45,×12asx12, and a deliberately near-duplicate company name changed to the more common spelling.
| Model | Coordinates | Box check | Small-text OCR | Same answer, 3 runs | Median latency |
|---|---|---|---|---|---|
| Opus 5.5 low | 27/27 | 12/12 | 149/153 | 1/3 | 4.0 s |
| Terra low | 27/27 | 12/12 | 138/153 | 3/3 | 2.3 s |
| Terra high | 27/27 | 12/12 | 138/153 | 3/3 | 3.2 s |
Limits
- Synthetic images only, from a single image set.
Desktop control
How does GPT-6.1 Terra compare with Opus 5.5, both at high effort, on a short Windows desktop task?
Setup
- Task: open a new Windows Character Map window, type
가Ω→42into the “Characters to copy” box, read the box back, read the selected font name, leave the window open, and end with one JSON line. - Command:
omp -p --mode json --tools=eval,read,bash,windows_controlat high effort. - Four runs in the order Terra, Opus, Opus, Terra. After each run the main agent graded it independently by reading the window's controls, then closed only that run's window.
Seconds per run
Results
- All four runs matched the expected input value, the font (Arial) and the reported window.
- Terra completed run 1 in 38 s (6 tool calls, 0 tool errors) and run 4 in 30 s (8 calls, 0 errors), while Opus completed run 2 in 43 s (9 calls, 1 error) and run 3 in 53 s (10 calls, 0 errors).
| Run | Model | Result | Time | Tool calls | Tool errors |
|---|---|---|---|---|---|
| 1 | GPT-6.1 Terra | Matched | 38 s | 6 | 0 |
| 2 | Opus 5.5 | Matched | 43 s | 9 | 1 |
| 3 | Opus 5.5 | Matched | 53 s | 10 | 0 |
| 4 | GPT-6.1 Terra | Matched | 30 s | 8 | 0 |
Limits
- One easy task with 2 runs per model. The maintainer did not test harder targets such as remote desktop windows or File Explorer.
Data and sources
The summary numbers for this page are in data.json. Raw run logs, prompts with machine details and account data stay private. All costs are catalogue-price conversions from token counts, not bills.