Check a model
Name what you are paying for. The plot is the same Pareto field as the frontier page. The answer is a computation on this catalogue, not an opinion. Bookmark the URL.
9 undominated of 134 · Aug 28, 2026
As of Aug 28, 2026, Gemma 4 26B A4B scores higher and costs less than GPT-5 Nano for Balanced on LMArena, but it is not a drop-in. You would give up: context, max output, file.
Gemma 4 26B A4B scores higher and costs less, but you would give up: context, max output, file.
Higher score, lower price, named losses
Not a drop-in. The loss is why these are not a recommendation.
| Model | LMArena | Effective $/M | You give up |
|---|---|---|---|
| Gemma 4 26B A4B | 1434.6 | $0.138/M | context, max output, file |
| DeepSeek V4 Flash 0423 | 1431.6 | $0.101/M | image, file |
| Qwen3.5-Flash | 1397.6 | $0.114/M | max output, file |
| Qwen3 30B A3B Instruct 2507 | 1384.3 | $0.084/M | context, max output, image, file, reasoning |
| Solar Pro 4 | 1376.2 | $0.052/M | image, file |
This page does not mail you. The URL is the watch: same model, same mix, current catalogue.