GPT-6 Sol (Low) vs gpt-oss-20b (High)
Which is better for the money: GPT-6 Sol (Low) by OpenAI or gpt-oss-20b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-6 Sol (Low) scores 25.2 points higher (34.2 vs 9.0) but costs 9.3× as much to run the benchmark ($269 vs $28.8; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6 Sol (Low) when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | GPT-6 Sol (Low) | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.2 | 9.0 | −73.7% gpt-oss-20b (High) is 73.7% less intelligent |
| Total AA cost (lower is better) | $268.73 | $28.81 | −89.3% gpt-oss-20b (High) is 89.3% cheaper |
| End-to-end time (lower is better) | 6.10s | 15.12s | +147.9% gpt-oss-20b (High) is 147.9% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
gpt-oss-20b (High) vs GPT-6 Sol (Low): 73.7% less intelligence, 89.3% less cost to run the AA benchmark, and 147.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Sol (Low) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- 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 Sol (Low)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-sol-low/gpt-oss-20b · Markdown: /api/v1/compare/gpt-6-sol-low/gpt-oss-20b?format=md · llms.txt · agent skill