gpt-oss-20b (High) vs Granite 4.2 3B
Which is better for the money: gpt-oss-20b (High) by OpenAI or Granite 4.2 3B by IBM? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Granite 4.2 3B
Granite 4.2 3B vs gpt-oss-20b (High): 1.1% more intelligence, 48.2% less cost to run the AA benchmark, and 228.2% slower end-to-end.
| Metric | gpt-oss-20b (High) | Granite 4.2 3B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 9.1 | +1.1% Granite 4.2 3B is 1.1% more intelligent |
| Total AA cost (lower is better) | $28.81 | $14.91 | −48.2% Granite 4.2 3B is 48.2% cheaper |
| End-to-end time (lower is better) | 15.23s | 49.98s | +228.2% Granite 4.2 3B is 228.2% slower |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.03 / $0.12 | |
| Input modalities | Text | Text |
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Granite 4.2 3B is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
gpt-oss-20b (High)Granite 4.2 3BToday's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-oss-20b/granite-4-2-3b · Markdown: /api/v1/compare/gpt-oss-20b/granite-4-2-3b?format=md · llms.txt · agent skill