Skip to content
SOLVENCY
Request a demo

Account controls are loading.

Head to head

Gemini 3.1 Pro (preview)vsUI-TARS 7B

For tasks, about a month.

No verdict

One cost is modelled and the other is measured. The two bases are never ranked against each other, so no verdict is given. Each figure is shown on its own basis below.

Verified pricing, pass rate and cost per solved task for Gemini 3.1 Pro (preview) and UI-TARS 7B
FigureGemini 3.1 Pro (preview)UI-TARS 7B
Input $/Mtok$2$0.1
Output $/Mtok$12$0.2
Cached input $/Mtok$0.2$0.1
Pass rate46%25%
Cost per solved task$1.91modelled$0.0003measured
Cost per month$382$0.05

Cost per month against tasks per month · drag the marker

Monthly cost against tasks per monthLog-log lines for UI-TARS 7B (measured, $0.0003 per solved task), Gemini 3.1 Pro (preview) (modelled, $1.91 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks.101001k10k100k$0.01$0.1$1$10$100$1k$10k$100kTASKS / MONTH (log) →200 tasksUI-TARS 7B · MEASURED · $0.0003 per solved task$0.05Gemini 3.1 Pro (preview) · MODELED · $1.91 per solved task$382— UI-TARS 7B · MEASURED— Gemini 3.1 Pro (preview) · MODELED

Solid measured · dashed modeled · dotted stale. The gap is the verdict.

Source: Scale SEAL leaderboard, SWE-bench Pro · verified 2026-08-21 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings