Skip to content
fedi.software

Qwen3.5-122B-A10B in fedi-index

The score in every slice, what it is made of, value, local run and history.

fedi-index · General

B 1,391 ±2

Percentile 63 · #110 · provisional

People prefer / Solves tasks

1,402 / —

Human votes vs benchmarks, Elo-eq

Value

+14

$0.9588 per 1M tokens, median of 20 providers · vendor $1.10

On your hardware

  • GPU 12 GB #6 · UD-IQ4_NL · ≈10 tok/s
  • GPU 24 GB #10 · Q4_K_S · ≈11 tok/s
  • Mac 64 GB #4 · UD-IQ3_XXS · ≈44 tok/s
  • 128 GB unified memory #9 · Q6_K · ≈15 tok/s

Score decomposition

B General 1,391 [1,388–1,393] Percentile 63 · #110 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,417 ±2.18 1,417 ±2 25.8% 2026-10-02 —
LMArena text/hard_prompts 1,421 ±2.65 1,414 ±2 25.7% 2026-10-02 —
LMArena text/instruction_following 1,399 ±3.35 1,412 ±3 12.6% 2026-10-02 —
LMArena text/expert 1,431 ±5.86 1,420 ±5 12.0% 2026-10-02 —
LMArena text/longer_query 1,410 ±3.21 1,410 ±3 6.3% 2026-10-02 —
LMArena text/multi_turn 1,416 ±4.40 1,413 ±4 6.2% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Coding 1,391 [1,388–1,394] Percentile 64 · #102 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,360 ±3.89 1,410 ±1 46.1% 2026-10-01 —
LMArena text/coding 1,436 ±3.61 1,413 ±3 44.3% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Math 1,395 [1,383–1,406] Percentile 66 · #86 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,432 ±6.99 1,424 ±7 87.0% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Vision 1,410 [1,406–1,414] Percentile 52 · #55 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,245 ±3.47 1,425 ±3 63.3% 2026-10-02 —
LMArena vision/ocr 1,251 ±3.67 1,424 ±4 15.6% 2026-10-02 —
LMArena vision/diagram 1,250 ±5.51 1,419 ±5 14.9% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Writing 1,388 [1,382–1,394] Percentile 60 · #109 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,368 ±4.72 1,396 ±5 61.2% 2026-10-02 —
LMArena text/longer_query 1,410 ±3.21 1,410 ±3 32.5% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: 繁體中文 1,408 [1,399–1,418] Percentile 64 · #82 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,462 ±6.66 1,423 ±5 93.4% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: Deutsch 1,403 [1,381–1,424] Percentile 59 · #59 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,425 ±14 1,424 ±12 90.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: English 1,405 [1,399–1,411] Percentile 65 · #95 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,429 ±2.96 1,418 ±3 93.9% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: Español 1,404 [1,387–1,420] Percentile 50 · #75 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,424 ±9.72 1,421 ±9 92.2% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: Français 1,407 [1,390–1,425] Percentile 49 · #69 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,442 ±10 1,425 ±10 91.9% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: 한국어 1,382 [1,363–1,401] Percentile 39 · #83 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,352 ±14 1,399 ±11 91.4% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: Polski 1,388 [1,370–1,406] Percentile 37 · #83 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,397 ±12 1,405 ±10 91.7% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

B Language: Русский 1,393 [1,385–1,402] Percentile 57 · #101 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,399 ±5.19 1,406 ±5 93.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

History

fedi-index by month
The same in a table
Model 2026-10
Qwen3.5-122B-A10B 1,391 B

Badge

Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.

fedi-index: Qwen3.5-122B-A10B

Data CC BY 4.0: keep the link to fedi.software.