fedi-index: peringkat model AI berbasis data terbuka
Peringkat model bahasa versi kami sendiri: suara preferensi manusia dan hasil benchmark independen dalam satu skala, lengkap dengan ketidakpastian dan rincian setiap skor.
Data langsung 2026-10 (dihitung ulang setiap hari) · Metodologi v1 · Metodologi · Riwayat · JSON
| # | Tier | Model | fedi-index | Persentil | Disukai orang | Menyelesaikan tugas | Nilai | Sumber | Rincian skor |
|---|---|---|---|---|---|---|---|---|---|
| 14 | S | 1.466 ±6 | 96 | 1.466 | 1.465 | +44 | AE | › | |
| 24 | A | 1.457 ±6 | 92 | 1.460 | 1.453 | +60 | AE | › | |
| 25 | A | 1.456 ±5 | 92 | 1.474 | — | +93◆ | A | › | |
| 31 | A | 1.448 ±10 | 90 | 1.452 | 1.441 | +92◆ | AE | › | |
| 33 | A | 1.448 ±6 | 89 | 1.459 | 1.432 | +105◆ | AE | › | |
| 36 | A | 1.443 ±2 | 88 | 1.457 | — | +80 | A | › | |
| 37 | A | 1.442 ±5 | 88 | 1.453 | 1.427 | +45 | AE | › | |
| 47 | A | 1.435 ±11 | 84 | — | 1.454 | +40 | E | › | |
| 48 | A | 1.435 ±5 | 84 | 1.443 | 1.423 | +44 | AE | › | |
| 50 | A | 1.433 ±4 | 83 | 1.449 | — | +98◆ | A | › | |
| 51 | A | 1.432 ±5 | 83 | 1.445 | 1.415 | +36 | AE | › | |
| 54 | A | 1.427 ±5 | 82 | 1.437 | 1.415 | +33 | AE | › | |
| 57 | A | 1.425 ±7 | 81 | 1.432 | 1.416 | +46 | AE | › | |
| 58 | A | 1.424 ±13 | 80 | — | 1.445 | +89 | E | › | |
| 65 | B | 1.418 ±6 | 78 | 1.426 | 1.407 | +26 | AE | › | |
| 66 | B | 1.418 ±5 | 78 | 1.430 | 1.405 | +36 | AE | › | |
| 73 | B | 1.413 ±8 | 75 | 1.424 | 1.392 | +50 | AE | › | |
| 74 | B | 1.412 ±5 | 75 | 1.425 | 1.396 | +27 | AE | › | |
| 75 | B | 1.412 ±6 | 75 | 1.428 | 1.390 | +23 | AE | › | |
| 77 | B | 1.411 ±3 | 74 | 1.425 | — | +33 | A | › | |
| 78 | B | 1.411 ±3 | 74 | 1.424 | — | +68 | A | › | |
| 79 | B | 1.411 ±2 | 73 | 1.423 | — | +75 | A | › | |
| 81 | B | 1.407 ±7 | 73 | 1.419 | 1.392 | +71 | AE | › | |
| 82 | B | 1.407 ±6 | 72 | 1.403 | 1.413 | +38 | AE | › | |
| 88 | B | 1.404 ±2 | 70 | 1.416 | — | +26 | A | › | |
| 94 | B | 1.400 ±11 | 68 | — | 1.416 | +9 | E | › | |
| 97 | B | 1.398 ±7 | 67 | 1.426 | 1.359 | +58 | AE | › | |
| 98 | B | 1.398 ±6 | 67 | 1.416 | 1.373 | +20 | AE | › | |
| 100 | B | 1.396 ±3 | 66 | 1.408 | — | +18 | A | › | |
| 102 | B | 1.395 ±8 | 65 | 1.406 | 1.383 | +46 | AE | › | |
| 104 | B | 1.394 ±4 | 65 | 1.407 | — | +27 | A | › | |
| 105 | B | 1.394 ±10 | 64 | 1.402 | 1.375 | +32 | AE | › | |
| 108 | B | 1.391 ±8 | 63 | 1.416 | 1.358 | +54 | AE | › | |
| 110 | B | 1.391 ±2 | 63 | 1.402 | — | +14 | A | › | |
| 111 | B | 1.390 ±6 | 62 | 1.403 | — | +31 | A | › | |
| 113 | B | 1.388 ±3 | 62 | 1.400 | — | +32 | A | › | |
| 116 | B | 1.387 ±2 | 61 | 1.398 | — | +55◆ | A | › | |
| 117 | B | 1.386 ±8 | 60 | 1.409 | 1.356 | -19 | AE | › | |
| 118 | B | 1.386 ±2 | 60 | 1.397 | — | +14 | A | › | |
| 121 | B | 1.381 ±2 | 59 | 1.392 | — | +50 | A | › | |
| 122 | B | 1.381 ±11 | 59 | — | 1.395 | +2 | E | › | |
| 125 | B | 1.380 ±3 | 58 | 1.391 | — | +18 | A | › | |
| 129 | B | 1.378 ±14 | 56 | — | 1.391 | -2 | E | › | |
| 130 | B | 1.377 ±10 | 56 | 1.399 | 1.340 | +19 | AE | › | |
| 131 | B | 1.376 ±7 | 56 | 1.383 | 1.365 | +11 | AE | › | |
| 133 | B | 1.374 ±4 | 55 | 1.386 | — | -17 | A | › | |
| 138 | B | 1.371 ±9 | 53 | 1.357 | 1.392 | +9 | AE | › | |
| 144 | B | 1.360 ±15 | 51 | — | 1.375 | +2 | E | › | |
| 147 | B | 1.356 ±9 | 50 | 1.375 | 1.320 | +25 | AE | › | |
| 149 | C | 1.356 ±4 | 49 | 1.366 | — | +0 | A | › | |
| 150 | C | 1.356 ±9 | 49 | 1.363 | 1.346 | -22 | AE | › | |
| 151 | C | 1.356 ±2 | 49 | 1.365 | — | -2 | A | › | |
| 157 | C | 1.347 ±6 | 47 | 1.357 | — | -12 | A | › | |
| 158 | C | 1.346 ±3 | 46 | 1.356 | — | -10 | A | › | |
| 160 | C | 1.344 ±3 | 46 | 1.353 | — | -22 | A | › | |
| 161 | C | 1.344 ±8 | 45 | 1.345 | 1.341 | -2 | AE | › | |
| 167 | C | 1.332 ±4 | 43 | 1.342 | 1.286 | +1 | AE | › | |
| 170 | C | 1.330 ±16 | 42 | — | 1.342 | +4 | E | › | |
| 171 | C | 1.330 ±4 | 42 | 1.338 | — | -32 | A | › | |
| 176 | C | 1.325 ±2 | 40 | 1.333 | — | -30 | A | › | |
| 177 | C | 1.324 ±3 | 40 | 1.332 | — | +6 | A | › | |
| 179 | C | 1.321 ±2 | 39 | 1.329 | — | -36 | A | › | |
| 183 | C | 1.317 ±3 | 38 | 1.325 | — | -14 | A | › | |
| 184 | C | 1.316 ±5 | 37 | 1.323 | — | -60 | A | › | |
| 185 | C | 1.315 ±6 | 37 | 1.323 | — | -40 | A | › | |
| 186 | C | 1.310 ±6 | 37 | 1.318 | — | -14 | A | › | |
| 187 | C | 1.309 ±9 | 36 | 1.309 | 1.310 | -29 | AE | › | |
| 189 | C | 1.303 ±7 | 36 | 1.310 | — | — | A | › | |
| 195 | C | 1.293 ±9 | 34 | 1.273 | 1.325 | -26 | AE | › | |
| 202 | C | 1.282 ±5 | 31 | 1.288 | — | -28 | A | › | |
| 203 | C | 1.279 ±3 | 31 | 1.284 | — | — | A | › | |
| 208 | C | 1.266 ±5 | 29 | 1.270 | — | -95 | A | › | |
| 226 | D | 1.199 ±5 | 23 | 1.198 | — | -133 | A | › | |
| 234 | D | 1.169 ±3 | 20 | 1.167 | — | -236 | A | › |
AArena (suara manusia)EEpoch AI (benchmark) ◆ Frontier Pareto: tidak ada yang lebih baik sekaligus lebih murah
fedi-index adalah setara Elo pada skala tetap: dapat dibandingkan antarbulan dalam satu versi metodologi. Tier S–D: berdasarkan persentil di kategori, dan tidak lebih tinggi dari yang diizinkan interval kepercayaan (ambang batas ada di metodologi). “Sementara” — hanya satu keluarga sumber yang mengukur model ini di sini. Metodologi
Nilai: kualitas sebanding harga
Setiap titik adalah model dengan API berbayar: fedi-index terhadap harga gabungan (3 input : 1 output, median penyedia). Garisnya adalah frontier Pareto — model yang tidak terkalahkan sekaligus dalam kualitas dan harga.
Frontier Pareto: 9 model
- Qwen3.7 Flash 1.364 · US$0,055
- Solar Pro 4 1.370 · US$0,105
- MiMo-V2-Flash 1.387 · US$0,15
- MiMo-V2.6-Flash 1.433 · US$0,175
- GLM 5.3 Flash 1.448 · US$0,2375
- DeepSeek V4.1 Flash 1.448 · US$0,42
- MiMo-V2.6-Pro 1.456 · US$0,5438
- Gemini 3.8 Flash 1.472 · US$1,50
- Claude Opus 5.5 1.504 · US$8
Di perangkat Anda
Peringkat model terbuka pada perangkat rumahan yang umum: skor umum, dikurangi jika generasi lebih lambat dari kecepatan nyaman atau kuantisasi di bawah Q4.
GPU 12 GB
- 1 Qwen3 Next 80B A3B Instruct Q5_K_M · sebagian di RAM ≈24 tok/s 62
- 2 Gemma 4 26B A4B UD-Q8_K_XL · sebagian di RAM ≈15 tok/s 54
- 3 Qwen3.5-35B-A3B Q8_0 · sebagian di RAM ≈18 tok/s 52
- 4 Qwen3.6 35B A3B UD-Q8_K_XL · sebagian di RAM ≈17 tok/s 47
- 5 Qwen3 Next 80B A3B Thinking Q5_K_M · sebagian di RAM ≈24 tok/s 46
- 6 Qwen3.5-122B-A10B UD-IQ4_NL · sebagian di RAM ≈10 tok/s 45
- 7 Qwen3 30B A3B Instruct 2507 Q8_0 · sebagian di RAM ≈16 tok/s 45
- 8 gpt-oss-120b MXFP4 · sebagian di RAM ≈19 tok/s 44
- 9 Qwen3.5-9B Q6_K ≈36 tok/s 42
- 10 Qwen3.8 27B UD-Q4_K_XL · sebagian di RAM ≈4 tok/s 37
GPU 24 GB
- 1 Qwen3.8 27B UD-Q5_K_S ≈38 tok/s 81
- 2 Gemma 4 31B Q4_1 ≈37 tok/s 67
- 3 Gemma 4 26B A4B UD-Q5_K_S ≈129 tok/s 63
- 4 Qwen3 Next 80B A3B Instruct UD-Q6_K_XL · sebagian di RAM ≈26 tok/s 62
- 5 Qwen3.5-27B Q5_K_S ≈38 tok/s 60
- 6 Qwen3.6 27B Q5_K_S ≈37 tok/s 59
- 7 Qwen3.5-35B-A3B Q4_K_S ≈191 tok/s 56
- 8 Qwen3.6 35B A3B UD-Q4_K_S ≈189 tok/s 51
- 9 Qwen3 30B A3B Instruct 2507 Q5_K_S ≈147 tok/s 50
- 10 Qwen3.5-122B-A10B Q4_K_S · sebagian di RAM ≈11 tok/s 47
Mac 64 GB
- 1 Qwen3.8 27B Q8_0 ≈13 tok/s 64
- 2 Gemma 4 26B A4B UD-Q8_K_XL ≈40 tok/s 63
- 3 Qwen3 Next 80B A3B Instruct Q4_K_S ≈84 tok/s 62
- 4 Qwen3.5-122B-A10B UD-IQ3_XXS ≈44 tok/s 56
- 5 Qwen3.5-35B-A3B Q8_0 ≈51 tok/s 56
- 6 Qwen3.6 35B A3B UD-Q8_K_XL ≈49 tok/s 51
- 7 Gemma 4 31B Q8_0 ≈11 tok/s 50
- 8 Qwen3 30B A3B Instruct 2507 Q8_0 ≈45 tok/s 50
- 9 Qwen3.5-27B Q8_0 ≈13 tok/s 48
- 10 Qwen3.6 27B Q8_0 ≈13 tok/s 47
Memori terpadu 128 GB
- 1 DeepSeek V4 Flash 0423 UD-IQ3_XXS ≈26 tok/s 65
- 2 Inkling Small UD-IQ3_S ≈23 tok/s 65
- 3 MiniMax M2.7 UD-IQ4_NL ≈20 tok/s 64
- 4 Gemma 4 26B A4B UD-Q8_K_XL ≈29 tok/s 63
- 5 Qwen3 Next 80B A3B Instruct Q8_0 ≈36 tok/s 62
- 6 Qwen3.8 27B UD-Q4_K_M ≈10 tok/s 58
- 7 Qwen3.5-35B-A3B Q8_0 ≈37 tok/s 56
- 8 Step 3.5 Flash IQ4_XS ≈17 tok/s 55
- 9 Qwen3.5-122B-A10B Q6_K ≈15 tok/s 54
- 10 DeepSeek V4 Flash 0731 UD-IQ3_XXS ≈11 tok/s 53
CPU, RAM 32 GB
- 1 Gemma 4 26B A4B UD-Q4_K_XL ≈6 tok/s 36
- 2 Qwen3.5-35B-A3B Q4_K_M ≈7 tok/s 32
- 3 Qwen3.6 35B A3B UD-Q4_K_XL ≈7 tok/s 30
- 4 Qwen3 30B A3B Instruct 2507 Q4_K_M ≈6 tok/s 28
- 5 Qwen3.8 27B UD-Q4_K_XL ≈2 tok/s 27
- 6 GLM 4.7 Flash Q4_K_M ≈6 tok/s 24
- 7 Nemotron 3 Nano 30B A3B Q4_K_M ≈7 tok/s 23
- 8 Gemma 4 31B Q4_K_M ≈2 tok/s 22
- 9 Qwen3 30B A3B Q4_K_M ≈6 tok/s 21
- 10 Qwen3.5-27B Q4_K_M ≈2 tok/s 21
Kecocokan dan kecepatan adalah perkiraan kami (bobot + KV cache dibandingkan memori, kecepatan dari bandwidth). Cek perangkat Anda: Bisakah berjalan lokal?
Sematkan di situs Anda
Tabel sebagai widget untuk situs Anda: diperbarui otomatis dan tetap mencantumkan atribusi sumber.