Skip to content
fedi.software

qwen1.5-110b-chat in fedi-index

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

fedi-index · General

D 1,183 ±3

Percentile 22 · #230 · provisional

People prefer / Solves tasks

1,182 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,183 [1,180–1,187] Percentile 22 · #230 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,175 ±2.81 1,174 ±3 26.4% 2026-10-02 —
LMArena text/hard_prompts 1,168 ±4.45 1,185 ±4 25.5% 2026-10-02 —
LMArena text/instruction_following 1,158 ±4.10 1,184 ±4 12.8% 2026-10-02 —
LMArena text/expert 1,144 ±8.42 1,185 ±7 11.3% 2026-10-02 —
LMArena text/multi_turn 1,160 ±5.85 1,181 ±5 6.1% 2026-10-02 —
LMArena text/longer_query 1,157 ±6.02 1,174 ±6 6.0% 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 Coding 1,190 [1,182–1,198] Percentile 21 · #221 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,184 ±5.23 1,189 ±5 89.8% 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 Math 1,189 [1,180–1,199] Percentile 23 · #197 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,185 ±5.76 1,187 ±6 87.6% 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 Writing 1,174 [1,166–1,182] Percentile 22 · #208 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,148 ±5.90 1,171 ±6 61.8% 2026-10-02 —
LMArena text/longer_query 1,157 ±6.02 1,174 ±6 31.5% 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

D Language: 繁體中文 1,218 [1,209–1,228] Percentile 18 · #182 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,206 ±6.77 1,220 ±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

D Language: Deutsch 1,166 [1,149–1,183] Percentile 12 · #127 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,123 ±11 1,163 ±9 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

D Language: English 1,176 [1,169–1,184] Percentile 23 · #211 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,198 ±3.70 1,175 ±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

D Language: Español 1,164 [1,139–1,189] Percentile 6 · #140 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,142 ±16 1,160 ±14 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 Language: Français 1,163 [1,136–1,190] Percentile 7 · #126 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,150 ±17 1,158 ±16 88.5% 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

D Language: 日本語 1,185 [1,166–1,203] Percentile 9 · #116 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,074 ±14 1,183 ±10 91.6% 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: 한국어 1,167 [1,152–1,182] Percentile 7 · #127 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,043 ±11 1,164 ±8 92.4% 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

D Language: Русский 1,157 [1,147–1,167] Percentile 12 · #207 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,118 ±6.23 1,154 ±6 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

History

fedi-index by month
The same in a table
Model 2026-10
qwen1.5-110b-chat 1,183 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: qwen1.5-110b-chat

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