Head to head
vs For light moderate heavy
No verdict
One cost is measured and the other is modelled . The two bases are never ranked against each other, so no verdict is given. Each figure is shown on its own basis below.
Copy link Save scenario Export compare table Planned
Verified pricing, pass rate and cost per solved task for Claude Opus 5 and Gemini 3.1 Pro (preview) Figure Claude Opus 5 Gemini 3.1 Pro (preview) Input $/Mtok $5 $2 Output $/Mtok $25 $12 Cached input $/Mtok $0.5 $0.2 Pass rate 100% 46% Cost per solved task $0.10 measured $1.91 modelled Cost per month $19 $382
Cost per month against tasks per month · drag the marker
Monthly cost against tasks per month Log-log lines for Claude Opus 5 (measured, $0.10 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. 10 100 1k 10k 100k $1 $10 $100 $1k $10k $100k TASKS / MONTH (log) → 200 tasks Claude Opus 5 · MEASURED · $0.10 per solved task $19 Claude Opus 5 MEASURED Gemini 3.1 Pro (preview) · MODELED · $1.91 per solved task $382 Gemini 3.1 Pro (prev… MODELED Monthly cost against tasks per month Log-log lines for Claude Opus 5 (measured, $0.10 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. 10 100 1k 10k 100k $1 $10 $100 $1k $10k $100k TASKS / MONTH (log) → 200 tasks Claude Opus 5 · MEASURED · $0.10 per solved task $19 Gemini 3.1 Pro (preview) · MODELED · $1.91 per solved task $382 — Claude Opus 5 · MEASURED — Gemini 3.1 Pro (preview) · MODELED Solid measured · dashed modeled · dotted stale. The gap is the verdict.
Solvency Bench (solvency.dev) — first-party measurement · verified 2026-08-21 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings