Skip to content
fedi.software

qwen1.5-14b-chat in fedi-index

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

fedi-index · General

D 1,142 ±4

Percentile 17 · #243 · provisional

People prefer / Solves tasks

1,138 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,142 [1,138–1,146] Percentile 17 · #243 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,128 ±3.59 1,128 ±4 26.7% 2026-10-02 —
LMArena text/hard_prompts 1,113 ±5.37 1,136 ±5 25.6% 2026-10-02 —
LMArena text/instruction_following 1,102 ±5.04 1,130 ±5 12.8% 2026-10-02 —
LMArena text/expert 1,094 ±10 1,144 ±8 10.8% 2026-10-02 —
LMArena text/multi_turn 1,110 ±7.28 1,136 ±7 5.9% 2026-10-02 —
LMArena text/longer_query 1,113 ±7.50 1,132 ±7 5.8% 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

D Coding 1,153 [1,143–1,164] Percentile 17 · #232 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,138 ±6.50 1,148 ±6 89.3% 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

D Math 1,139 [1,128–1,150] Percentile 15 · #217 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,125 ±6.87 1,130 ±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

D Writing 1,125 [1,115–1,135] Percentile 14 · #230 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,091 ±7.17 1,112 ±7 61.6% 2026-10-02 —
LMArena text/longer_query 1,113 ±7.50 1,132 ±7 31.3% 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

D Language: 繁體中文 1,175 [1,165–1,185] Percentile 14 · #192 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,147 ±7.12 1,173 ±6 93.3% 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

D Language: Deutsch 1,104 [1,083–1,124] Percentile 3 · #140 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,042 ±13 1,094 ±11 91.0% 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

D Language: English 1,127 [1,118–1,136] Percentile 16 · #230 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,148 ±4.51 1,122 ±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

D Language: Русский 1,097 [1,084–1,110] Percentile 4 · #224 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,046 ±7.88 1,088 ±7 92.9% 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

History

fedi-index by month
The same in a table
Model 2026-10
qwen1.5-14b-chat 1,142 D

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: qwen1.5-14b-chat

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