Skip to content
fedi.software

qwen2.5-plus-1127 in fedi-index

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

fedi-index · General

C 1,289 ±4

Percentile 33 · #197 · provisional

People prefer / Solves tasks

1,294 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,289 [1,285–1,293] Percentile 33 · #197 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,299 ±3.23 1,299 ±3 26.9% 2026-10-02 —
LMArena text/hard_prompts 1,299 ±5.39 1,304 ±5 25.4% 2026-10-02 —
LMArena text/instruction_following 1,275 ±4.60 1,294 ±4 13.0% 2026-10-02 —
LMArena text/expert 1,289 ±11 1,304 ±9 10.5% 2026-10-02 —
LMArena text/multi_turn 1,299 ±6.77 1,307 ±6 6.0% 2026-10-02 —
LMArena text/longer_query 1,292 ±7.20 1,299 ±7 5.9% 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

C Coding 1,294 [1,283–1,305] Percentile 32 · #190 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,314 ±7.05 1,305 ±6 89.1% 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

C Math 1,283 [1,271–1,294] Percentile 32 · #173 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,297 ±7.02 1,295 ±7 86.9% 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

C Writing 1,285 [1,275–1,295] Percentile 34 · #178 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,262 ±7.33 1,287 ±8 61.1% 2026-10-02 —
LMArena text/longer_query 1,292 ±7.20 1,299 ±7 31.8% 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

C Language: 繁體中文 1,297 [1,281–1,314] Percentile 28 · #161 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,314 ±11 1,305 ±9 92.1% 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

C Language: English 1,299 [1,291–1,307] Percentile 36 · #176 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,322 ±4.01 1,306 ±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: 日本語 1,274 [1,252–1,297] Percentile 17 · #106 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,206 ±17 1,282 ±12 90.5% 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

C Language: Русский 1,284 [1,272–1,297] Percentile 26 · #173 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,271 ±7.72 1,291 ±7 93.0% 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

History

fedi-index by month
The same in a table
Model 2026-10
qwen2.5-plus-1127 1,289 C

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: qwen2.5-plus-1127

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