GPT-6.1 Terra (Xhigh) vs gpt-oss-20b (High)
Which is better for the money: GPT-6.1 Terra (Xhigh) by OpenAI or gpt-oss-20b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Terra (Xhigh) scores 36.4 points higher (45.4 vs 9.0) but costs 13× as much to run the benchmark ($365 vs $28.8; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Terra (Xhigh) when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | GPT-6.1 Terra (Xhigh) | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 45.4 | 9.0 | −80.2% gpt-oss-20b (High) is 80.2% less intelligent |
| Total AA cost (lower is better) | $364.95 | $28.81 | −92.1% gpt-oss-20b (High) is 92.1% cheaper |
| End-to-end time (lower is better) | 18.82s | 13.99s | −25.7% gpt-oss-20b (High) is 25.7% faster |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
gpt-oss-20b (High) vs GPT-6.1 Terra (Xhigh): 80.2% less intelligence, 92.1% less cost to run the AA benchmark, and 25.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- 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-6.1 Terra (Xhigh)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-6-1-terra-xhigh/gpt-oss-20b · Markdown: /api/v1/compare/gpt-6-1-terra-xhigh/gpt-oss-20b?format=md · llms.txt · agent skill