Updates | SolvePlot

Learn

12 Desmos skills lessons

The Desmos skills course now has guided examples, editable calculators, and checks throughout each lesson.

Desmos lessons: 12
In-lesson checks: 49
Checkpoints: 3

Work from functions and tables through regression, restrictions, and coordinate shortcuts.
Practise with 49 in-lesson checks and three four-question checkpoints. Answer feedback, hints, and worked explanations are included.
The SAT math lessons are unchanged in this update.

Learn

Resume lessons and see your progress

Leaving a lesson saves your place and answers on this device. The course page shows completed lessons, a suggested next step, and lessons you can resume.

Completion screens separate first-try answers, hints, and exercises worked through with help.
The course’s first-try percentage uses your best completed run per lesson. Hinted and assisted answers do not count as first-try correct.
Lesson accents follow your workspace palette. Candy keeps its green accent; other palettes use their own colors.
Answer fields, calculator spacing, section dividers, and mobile layouts have been refined.

Workspace

Loading screens that match each page

The solver, lessons, history, saved tricks, and account pages now use loading layouts shaped like the page you’re opening.

Sidebar navigation keeps the destination’s layout visible while its content loads.
History and saved tricks have cleaner card spacing, typography, and empty states.
These are interface changes; navigation speed was not benchmarked.

Solver

GPT-6 Luna Low is the solver default

The solver now uses GPT-6 Luna Low, keeping the Desmos-first strategy library and calculator checks. Explanations and the tutor also use Luna Low by default.

GPT-5-mini is no longer the active solver or tutor model, and there is no automatic fallback to it.
Existing bounded correction calls can still use more reasoning within Luna when needed.
The comparison below helped inform this choice. It is a small diagnostic, not a production speed or accuracy guarantee.

Recorded October 26, 2026

One problem, four configurations

One request per configuration on the same compact, text-only similarity problem. These are API request times, not full SolvePlot solve times.

Scroll the table to compare all columns

Single-request results on Bedrock Prep public Similarity 77m; expected answer 16
Model	Reasoning	Time	Reasoning tokens	API cost	Answer
GPT-6.1 Sol	Low	6.006 s	168	$0.009672	16Correct
GPT-6 LunaCurrent default	Low	6.819 s	716	$0.001072	16Correct
GPT-6 Luna	Medium	9.764 s	1,415	$0.001735	16Correct
GPT-5-mini	Low	17.322 s	2,304	$0.011275	100Incorrect

Did the calculator method work?

Sol Low and both Luna configurations produced working proportion regressions for the answer 16. Sol included a readout row. For each one-row Luna fit, an extra parameter readout was added only for the audit to confirm 16; that row was not model-generated.

GPT-5-mini answered 100 and produced an incomplete coordinate construction. Twelve of its fourteen original rows errored in Desmos, so no working method is credited.

Token counts and request settings

All four requests used 463 input tokens, 0 cached tokens, a 4,096-token output cap, Low verbosity, JSON mode, and requested Priority processing. There were no retries or separate explanation calls.

Configuration	Visible output	Total output	Original rows
GPT-6.1 Sol Low	223	391	2 · no errors
GPT-6 Luna Low	263	979	1 · no errors
GPT-6 Luna Medium	227	1,642	1 · no errors
GPT-5-mini Low	770	3,074	14 · 12 errors

Total output includes reasoning tokens. Sol and Luna returned the service-tier label Fast; Mini returned priority. Costs use the returned usage and applied tier.

What this comparison can tell us

Luna Low found the same useful proportion at a lower request cost in this test. A single attempt does not establish typical speed, accuracy, or reliability. The compact test excluded the full strategy library, production candidate selection, image input, and separate explanation generation.

Mini ran after the other three requests. Timing was not controlled for provider load, and no p50 or p95 is inferred. The listed costs are usage-derived API request costs, not customer prices or invoice totals.

Test sourceBedrock Prep · public Similarity 77m Public diagram