Skip to content
fedi.software

qwen1.5-7b-chat in fedi-index

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

fedi-index · General

D 1,105 ±6

Percentile 11 · #261 · provisional

People prefer / Solves tasks

1,098 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,105 [1,099–1,110] Percentile 11 · #261 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,083 ±4.95 1,083 ±5 32.2% 2026-10-02 —
LMArena text/hard_prompts 1,065 ±7.85 1,093 ±7 29.2% 2026-10-02 —
LMArena text/instruction_following 1,058 ±7.08 1,089 ±7 14.9% 2026-10-02 —
LMArena text/multi_turn 1,061 ±13 1,092 ±12 5.6% 2026-10-02 —
LMArena text/longer_query 1,090 ±15 1,111 ±14 4.7% 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 Coding 1,131 [1,115–1,147] Percentile 13 · #241 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,107 ±10 1,120 ±9 87.4% 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 Math 1,104 [1,087–1,120] Percentile 10 · #230 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,080 ±10 1,086 ±10 84.7% 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 Writing 1,084 [1,068–1,101] Percentile 8 · #247 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,035 ±11 1,055 ±12 63.5% 2026-10-02 —
LMArena text/longer_query 1,090 ±15 1,111 ±14 26.9% 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: 繁體中文 1,171 [1,150–1,192] Percentile 13 · #194 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,140 ±15 1,168 ±12 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 1,085 [1,074–1,096] Percentile 10 · #246 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,105 ±5.71 1,077 ±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
qwen1.5-7b-chat 1,105 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: qwen1.5-7b-chat

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