GPT-5.6 Luna (Medium) vs gpt-oss-20b (High)
Which is better for the money: GPT-5.6 Luna (Medium) by OpenAI or gpt-oss-20b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-5.6 Luna (Medium) scores 16.0 points higher (25.0 vs 9.0) but costs 1.5× as much to run the benchmark ($44.3 vs $28.8; both budget class). Pick GPT-5.6 Luna (Medium) when the extra intelligence is worth the premium, otherwise gpt-oss-20b (High).
| Metric | GPT-5.6 Luna (Medium) | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.0 | 9.0 | −64.0% gpt-oss-20b (High) is 64.0% less intelligent |
| Total AA cost (lower is better) | $44.32 | $28.81 | −35.0% gpt-oss-20b (High) is 35.0% cheaper |
| End-to-end time (lower is better) | 5.82s | 16.79s | +188.5% gpt-oss-20b (High) is 188.5% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
gpt-oss-20b (High) vs GPT-5.6 Luna (Medium): 64.0% less intelligence, 35.0% less cost to run the AA benchmark, and 188.5% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Medium) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
GPT-5.6 Luna (Medium)gpt-oss-20b (High)Today'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-5-6-luna-medium/gpt-oss-20b · Markdown: /api/v1/compare/gpt-5-6-luna-medium/gpt-oss-20b?format=md · llms.txt · agent skill