Skip to content
fedi.software

fedi-index: Language: Español

Best models for this language by Arena votes in it. Provisional: one source family.

Live data for 2026-10 (recalculated daily) · Methodology v1 · Methodology · History · JSON

All Open weights Closed
# Tier Model fedi-index Percentile Value Sources Score decomposition
11A1,450 ±1593 +45 A›
13A1,449 ±1292 +80 A›
15A1,448 ±1790 +44 A›
18A1,443 ±1288 +36 A›
24A1,441 ±1884 +105◆ A›
28A1,439 ±1482 +44 A›
31B1,434 ±1380 +33 A›
37B1,429 ±1576 +23 A›
38B1,428 ±1175 +36 A›
39B1,427 ±2074 +18 A›
44B1,424 ±2471 +33 A›
48B1,422 ±1168 +27 A›
49B1,422 ±2168 +46 A›
50B1,422 ±1667 +27 A›
51B1,421 ±2566 +68 A›
53B1,419 ±2165 +60 A›
60B1,415 ±1460 +71 A›
62B1,414 ±1659 +26 A›
64B1,413 ±2057 +32 A›
66B1,411 ±1356 +50 A›
69B1,410 ±1954 +38 A›
70B1,410 ±2653 +46 A›
72B1,405 ±2652 +20 A›
75B1,404 ±1650 +14 A›
78C1,402 ±2548 +19 A›
79C1,402 ±2347 +27 A›
80C1,402 ±1447 +55◆ A›
81C1,402 ±1246 +50 A›
83C1,396 ±1445 +75 A›
85C1,392 ±2543 +0 A›
88C1,389 ±1141 +32 A›
90C1,389 ±1740 +14 A›
93C1,385 ±1938 +25 A›
95C1,384 ±2636 -19 A›
101C1,379 ±2632 -17 A›
102C1,376 ±2332 +18 A›
103C1,376 ±1631 +11 A›
105C1,372 ±1830 -2 A›
106C1,370 ±1829 -2 A›
107C1,363 ±2628 -22 A›
114D1,358 ±2624 +6 A›
117D1,348 ±2022 -22 A›
120D1,346 ±1420 +9 A›
122D1,344 ±1818 -36 A›
123D1,343 ±2318 -10 A›
124D1,338 ±2417 +1 A›
126D1,334 ±2416 -14 A›
129D1,321 ±1814 -30 A›
131D1,310 ±2312 -29 A›
134D1,300 ±2410 — A›
139D1,171 ±217 -236 A›

…

AArena (human votes) ◆ Pareto frontier: nothing is both better and cheaper

fedi-index is an Elo-equivalent on a fixed scale: comparable between months within one methodology version. Tiers S–D: by percentile in the slice, and no better than the confidence interval allows (cut-offs in the methodology). This slice has one source family, so all its scores are provisional. Methodology