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, MiniMax M2.5 is dominated for Balanced on LMArena. Hy3 scores 82.2 higher and costs 69% less, with a covering envelope. 9 of 134 rated, priced standard models are undominated.
Hy3 is both better and cheaper than MiniMax M2.5.
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.
| Model | LMArena | Effective $/M | You save |
|---|---|---|---|
| Hy3 | 1441.2 +82.2 | $0.144/M | 69% |
| DeepSeek V4 Flash 0423 | 1431.6 +72.6 | $0.101/M | 79% |
| GPT-5.6 Luna | 1428.5 +69.5 | $0.450/M | 5% |
| MiMo-V2.5 | 1427.3 +68.3 | $0.175/M | 63% |
| Solar Pro 4 | 1376.2 +17.2 | $0.052/M | 89% |
| GPT-5.4 Nano | 1372.8 +13.8 | $0.463/M | 2% |
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 31B | 1441.7 | $0.153/M | max output |
| Gemma 4 26B A4B | 1434.6 | $0.138/M | max output |
| DeepSeek V3.2 | 1424.6 | $0.290/M | context |
| DeepSeek V3.2 Exp | 1424.4 | $0.305/M | context, max output |
| DeepSeek V3.1 Terminus | 1419.6 | $0.453/M | context, max output |
This page does not mail you. The URL is the watch: same model, same mix, current catalogue.