Skip to content
fedi.software

Qwen3.6 Plus in fedi-index

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

fedi-index · General

B 1,415 ±5

Percentile 77 · #68

People prefer / Solves tasks

1,423 / 1,404

Human votes vs benchmarks, Elo-eq

Value

+34

$1.12 per 1M tokens, median of 22 providers · vendor $1.12

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,415 [1,410–1,420] Percentile 77 · #68 · components: 9
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 148 ±0.96 1,419 ±8 33.6% 2026-03-31 —
LMArena text/overall 1,437 ±2.10 1,437 ±2 15.7% 2026-10-02 —
LMArena text/hard_prompts 1,449 ±2.45 1,439 ±2 15.7% 2026-10-02 —
LMArena text/instruction_following 1,424 ±3.01 1,436 ±3 7.7% 2026-10-02 —
LMArena text/expert 1,455 ±4.55 1,440 ±4 7.6% 2026-10-02 —
LMArena text/longer_query 1,440 ±2.88 1,437 ±3 3.9% 2026-10-02 —
Epoch AI simpleqa_verified decay ×0.61 0.44 ±0.02 1,436 ±5 3.8% 2026-08-27 —
LMArena text/multi_turn 1,438 ±3.81 1,433 ±4 3.8% 2026-10-02 —
Epoch AI gpqa_diamond decay ×0.26 0.88 ±0.02 1,451 ±11 1.2% 2026-08-07 —

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 1,411 [1,408–1,415] Percentile 74 · #73 · components: 3
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,461 ±2.84 1,438 ±1 40.2% 2026-10-01 —
LMArena text/coding 1,467 ±3.17 1,441 ±3 38.9% 2026-10-02 —
Epoch AI swe_bench_verified decay ×0.37 0.58 ±0.02 1,370 ±12 12.5% 2026-05-14 —

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 1,408 [1,401–1,416] Percentile 76 · #61 · components: 2
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,450 ±5.90 1,441 ±6 50.4% 2026-10-02 —
Epoch AI frontiermath_t1_3 decay ×0.86 0.38 ±0.03 1,404 ±6 42.4% 2026-08-30 —

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 1,420 [1,415–1,426] Percentile 76 · #66 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,405 ±4.01 1,433 ±4 61.7% 2026-10-02 —
LMArena text/longer_query 1,440 ±2.88 1,437 ±3 32.1% 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 1,420 [1,411–1,429] Percentile 73 · #61 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,477 ±6.06 1,435 ±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

B Language: Deutsch 1,427 [1,410–1,444] Percentile 77 · #34 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,452 ±11 1,447 ±10 92.0% 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 Language: English 1,422 [1,417–1,427] Percentile 74 · #72 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,446 ±2.73 1,436 ±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 1,411 [1,398–1,425] Percentile 55 · #67 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,431 ±8.08 1,427 ±8 92.8% 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: Français 1,420 [1,407–1,433] Percentile 63 · #50 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,455 ±7.89 1,437 ±7 92.8% 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: 日本語 1,400 [1,382–1,418] Percentile 52 · #62 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,389 ±14 1,418 ±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: 한국어 1,403 [1,388–1,418] Percentile 54 · #63 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,379 ±11 1,420 ±8 92.5% 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: Polski 1,419 [1,404–1,433] Percentile 65 · #47 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,434 ±9.54 1,436 ±8 92.5% 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: Русский 1,423 [1,416–1,430] Percentile 74 · #61 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,434 ±4.44 1,438 ±4 93.7% 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

History

fedi-index by month
The same in a table
Model 2026-10
Qwen3.6 Plus 1,415 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: Qwen3.6 Plus

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