DeepSeek V4.1 Flash (Non-reasoning) vs gpt-oss-20b (High)
Which is better for the money: DeepSeek V4.1 Flash (Non-reasoning) by DeepSeek 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
DeepSeek V4.1 Flash (Non-reasoning) scores 15.7 points higher (24.7 vs 9.0) but costs 8.3× as much to run the benchmark ($239 vs $28.8; mid-range vs budget cost classes). They are not alternatives at one budget: pick DeepSeek V4.1 Flash (Non-reasoning) when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | DeepSeek V4.1 Flash (Non-reasoning) | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.7 | 9.0 | −63.6% gpt-oss-20b (High) is 63.6% less intelligent |
| Total AA cost (lower is better) | $238.91 | $28.81 | −87.9% gpt-oss-20b (High) is 87.9% cheaper |
| End-to-end time (lower is better) | 2.74s | 15.12s | +451.8% gpt-oss-20b (High) is 451.8% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
gpt-oss-20b (High) vs DeepSeek V4.1 Flash (Non-reasoning): 63.6% less intelligence, 87.9% less cost to run the AA benchmark, and 451.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V4.1 Flash (Non-reasoning) 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.
DeepSeek V4.1 Flash (Non-reasoning)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/deepseek-v4-1-flash-non-reasoning/gpt-oss-20b · Markdown: /api/v1/compare/deepseek-v4-1-flash-non-reasoning/gpt-oss-20b?format=md · llms.txt · agent skill