Gemma 4 E4B (Reasoning) vs GPT-6.1 Terra (Non-reasoning)
Which is better for the money: Gemma 4 E4B (Reasoning) by Google or GPT-6.1 Terra (Non-reasoning) 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 (Non-reasoning) scores 24.6 points higher (33.5 vs 8.9) but costs 10× as much to run the benchmark ($154 vs $14.7; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Terra (Non-reasoning) when you need intelligence above 8.9, and Gemma 4 E4B (Reasoning) when 8.9 is enough.
| Metric | Gemma 4 E4B (Reasoning) | GPT-6.1 Terra (Non-reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.9 | 33.5 | +276.4% GPT-6.1 Terra (Non-re… is 3.8× more intelligent |
| Total AA cost (lower is better) | $14.68 | $153.58 | +946.2% GPT-6.1 Terra (Non-re… is 10× more expensive |
| End-to-end time (lower is better) | 54.54s | 6.76s | −87.6% GPT-6.1 Terra (Non-re… is 87.6% faster |
| Price per 1M tokens (in / out) | $0.02 / $0.10 | $1.00 / $5.00 | |
| Input modalities | Text, Image, Speech, Video | Text, Image |
GPT-6.1 Terra (Non-reasoning) vs Gemma 4 E4B (Reasoning): 276.4% more intelligence, 946.2% more cost to run the AA benchmark, and 87.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemma 4 E4B (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- GPT-6.1 Terra (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Gemma 4 E4B (Reasoning)GPT-6.1 Terra (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/gemma-4-e4b/gpt-6-1-terra-non-reasoning · Markdown: /api/v1/compare/gemma-4-e4b/gpt-6-1-terra-non-reasoning?format=md · llms.txt · agent skill