Skip to content
fedi.software

qwen1.5-32b-chat in fedi-index

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

fedi-index · General

D 1,160 ±4

Percentile 19 · #237

People prefer / Solves tasks

1,153 / 1,188

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,160 [1,156–1,165] Percentile 19 · #237 · components: 7
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,137 ±3.10 1,137 ±3 22.4% 2026-10-02 —
LMArena text/hard_prompts 1,130 ±4.71 1,152 ±4 21.6% 2026-10-02 —
Epoch AI gpqa_diamond decay ×0.26 0.31 ±0.02 1,183 ±9 15.5% 2025-01-27 —
LMArena text/instruction_following 1,116 ±4.35 1,144 ±4 10.8% 2026-10-02 —
LMArena text/expert 1,126 ±9.25 1,171 ±8 9.3% 2026-10-02 —
LMArena text/multi_turn 1,140 ±6.30 1,163 ±6 5.1% 2026-10-02 —
LMArena text/longer_query 1,146 ±6.39 1,163 ±6 5.0% 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 1,167 [1,158–1,175] Percentile 18 · #229 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,155 ±5.55 1,163 ±5 89.6% 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 Math 1,164 [1,154–1,174] Percentile 18 · #209 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,155 ±5.96 1,158 ±6 87.5% 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 Writing 1,123 [1,114–1,133] Percentile 14 · #231 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,083 ±6.26 1,104 ±6 73.2% 2026-10-02 —
LMArena text/longer_query outlier 1,146 ±6.39 1,163 ±6 18.7% 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: 繁體中文 1,197 [1,187–1,207] Percentile 15 · #190 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,176 ±6.81 1,196 ±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 1,115 [1,097–1,133] Percentile 6 · #135 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,058 ±12 1,107 ±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

D Language: English 1,139 [1,131–1,146] Percentile 19 · #222 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,160 ±3.91 1,134 ±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 1,121 [1,095–1,147] Percentile 3 · #144 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,089 ±16 1,111 ±15 88.9% 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

D Language: Français 1,122 [1,094–1,151] Percentile 4 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,100 ±18 1,111 ±16 87.8% 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 Language: 日本語 1,153 [1,131–1,176] Percentile 6 · #120 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,027 ±17 1,148 ±13 90.2% 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

D Language: 한국어 1,143 [1,121–1,165] Percentile 6 · #128 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,007 ±16 1,137 ±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

D Language: Русский 1,119 [1,108–1,130] Percentile 6 · #219 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,073 ±6.96 1,113 ±6 93.2% 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

History

fedi-index by month
The same in a table
Model 2026-10
qwen1.5-32b-chat 1,160 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: qwen1.5-32b-chat

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