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, GPT-5 Mini is dominated for Balanced on LMArena. GPT-5.6 Luna scores 55.1 higher and costs 35% less, with a covering envelope. 9 of 134 rated, priced standard models are undominated.

Current model

GPT-5 Mini

Balanced

3 tokens in per 1 out

GPT-5.6 Luna1428.5 · $0.450/MGPT-5 Mini1373.4 · $0.688/MLMArena EloEffective $/M · Balanced
134 rated, priced standard models. Chartreuse is the frontier. Cobalt is the model you named, when it is not on the staircase.

GPT-5.6 Luna is both better and cheaper than GPT-5 Mini.

GPT-5 Mini

LMArena Elo

1373.4

Effective $/M · Balanced

$0.688/M

GPT-5.6 Luna

LMArena Elo

1428.5

Effective $/M · Balanced

$0.450/M

Envelope-safe replacements

Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here.

ModelLMArenaEffective $/MYou save
GPT-5.6 Luna1428.5 +55.1$0.450/M35%

Higher score, lower price, named losses

Not a drop-in. The loss is why these are not a recommendation.

ModelLMArenaEffective $/MYou give up
MiMo-V2.5-Pro1465.0$0.544/Mimage, file
Qwen3.7 Plus1456.2$0.560/Mfile
Gemma 4 31B1441.7$0.153/Mcontext, max output, file
Hy31441.2$0.144/Mcontext, image, file
MiniMax M31434.8$0.525/Mfile

Open the frontier

This page does not mail you. The URL is the watch: same model, same mix, current catalogue.