Gemma 4 26B A4B (Non-reasoning) vs GPT-6 Luna (High)
Gemma 4 26B A4B (Non-reasoning) vs GPT-6 Luna (High). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.
Verdict
Comparison incomplete
A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.
| Metric | Gemma 4 26B A4B (Non-reasoning) | GPT-6 Luna (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 13.1 | 32.9 | +151.1% GPT-6 Luna (High) is 2.5× more intelligent |
| Total AA cost (lower is better) | Not reported | $47.85 | — not comparable |
| End-to-end time (lower is better) | 5.07s | 18.94s | +273.6% GPT-6 Luna (High) is 273.6% slower |
| Price per 1M tokens (in / out) | $0.12 / $0.40 | $0.10 / $0.50 | |
| Input modalities | Text, Image, Video | Text, Image |
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gemma-4-26b-a4b-non-reasoning/gpt-6-luna-high · Markdown: /api/v1/compare/gemma-4-26b-a4b-non-reasoning/gpt-6-luna-high?format=md · llms.txt · agent skill