Skip to content
SOLVENCY
Request a demo

Account controls are loading.

Head to head

gpt-oss-120bvsQwen3 32B

For tasks, about a month.

Verdict · measured basis

gpt-oss-120b costs $0.0011 per solved task against Qwen3 32B at $0.0016 — ▼ 1.5x cheaper. Over 200 tasks that is $0.11 a month.

On output token price alone gpt-oss-120b looks 1.6x cheaper. The ranking holds, but the margin changes.

Verified pricing, pass rate and cost per solved task for gpt-oss-120b and Qwen3 32B
Figuregpt-oss-120bQwen3 32B
Input $/Mtok$0.037$0.08
Output $/Mtok$0.17$0.28
Cached input $/Mtok$0.037$0.08
Pass rate60%83%
Cost per solved task$0.0011measured$0.0016measured
Cost per month$0.21$0.32

Cost per month against tasks per month · drag the marker

Monthly cost against tasks per monthLog-log lines for gpt-oss-120b (measured, $0.0011 per solved task), Qwen3 32B (measured, $0.0016 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks.101001k10k100k$0.01$0.1$1$10$100TASKS / MONTH (log) →200 tasksgpt-oss-120b · MEASURED · $0.0011 per solved task$0.21Qwen3 32B · MEASURED · $0.0016 per solved task$0.32— gpt-oss-120b · MEASURED— Qwen3 32B · MEASURED

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

Solvency Bench (solvency.dev) — first-party measurement · verified 2026-08-26 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings