DeepSeek V3 (Dec '24) vs gpt-oss-120b (High)
Which is better for the money: DeepSeek V3 (Dec '24) by DeepSeek or gpt-oss-120b (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-oss-120b (High) scores 3.1 points higher (11.6 vs 8.5) but costs 4.8× as much to run the benchmark ($123 vs $25.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick gpt-oss-120b (High) when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | gpt-oss-120b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 11.6 | +36.5% gpt-oss-120b (High) is 36.5% more intelligent |
| Total AA cost (lower is better) | $25.37 | $122.71 | +383.7% gpt-oss-120b (High) is 4.8× more expensive |
| End-to-end time (lower is better) | 11.84s | 11.61s | −1.9% gpt-oss-120b (High) is 1.9% faster |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.15 / $0.60 | |
| Input modalities | Text | Text |
gpt-oss-120b (High) vs DeepSeek V3 (Dec '24): 36.5% more intelligence, 383.7% more cost to run the AA benchmark, and 1.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
DeepSeek V3 (Dec '24)gpt-oss-120b (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-v3/gpt-oss-120b · Markdown: /api/v1/compare/deepseek-v3/gpt-oss-120b?format=md · llms.txt · agent skill