gpt-oss-20b (High) vs Grok 4.3 (Non-reasoning)
Which is better for the money: gpt-oss-20b (High) by OpenAI or Grok 4.3 (Non-reasoning) by SpaceXAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Grok 4.3 (Non-reasoning) scores 5.0 points higher (14.0 vs 9.0) but costs 8.7× as much to run the benchmark ($250 vs $28.8; mid-range vs budget cost classes). They are not alternatives at one budget: pick Grok 4.3 (Non-reasoning) when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | gpt-oss-20b (High) | Grok 4.3 (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 14.0 | +55.6% Grok 4.3 (Non-reasoni… is 55.6% more intelligent |
| Total AA cost (lower is better) | $28.81 | $250.37 | +769.0% Grok 4.3 (Non-reasoni… is 8.7× more expensive |
| End-to-end time (lower is better) | 14.83s | 5.86s | −60.5% Grok 4.3 (Non-reasoni… is 60.5% faster |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $1.25 / $2.50 | |
| Input modalities | Text | Text, Image |
Grok 4.3 (Non-reasoning) vs gpt-oss-20b (High): 55.6% more intelligence, 769.0% more cost to run the AA benchmark, and 60.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Grok 4.3 (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)Grok 4.3 (Non-reasoning)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-oss-20b/grok-4-3-non-reasoning · Markdown: /api/v1/compare/gpt-oss-20b/grok-4-3-non-reasoning?format=md · llms.txt · agent skill