Skip to content
fedi.software

ERNIE 5.0 (0110) in fedi-index

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

fedi-index · General

B 1,406 ±2

Percentile 69 · #93 · provisional

People prefer / Solves tasks

1,418 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,406 [1,404–1,408] Percentile 69 · #93 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,444 ±1.97 1,444 ±2 25.8% 2026-11-11 0110
LMArena text/hard_prompts 1,445 ±2.42 1,435 ±2 25.7% 2026-11-11 0110
LMArena text/instruction_following 1,413 ±3.08 1,425 ±3 12.6% 2026-11-11 0110
LMArena text/expert 1,426 ±5.56 1,416 ±4 12.0% 2026-11-11 0110
LMArena text/longer_query 1,421 ±3.07 1,420 ±3 6.3% 2026-11-11 0110
LMArena text/multi_turn 1,433 ±4.05 1,429 ±4 6.2% 2026-11-11 0110

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

B Coding 1,404 [1,398–1,409] Percentile 67 · #96 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,454 ±3.35 1,430 ±3 88.5% 2026-11-11 0110

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

B Math 1,399 [1,389–1,409] Percentile 66 · #88 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,436 ±6.30 1,428 ±6 87.3% 2026-11-11 0110

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 Vision 1,409 [1,402–1,416] Percentile 46 · #60 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,248 ±5.68 1,428 ±5 65.3% 2026-11-09 —
LMArena vision/ocr 1,249 ±7.20 1,423 ±7 15.0% 2026-11-09 —
LMArena vision/diagram 1,235 ±11 1,406 ±10 12.9% 2026-11-09 —

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

B Writing 1,428 [1,423–1,434] Percentile 76 · #63 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,426 ±4.17 1,455 ±4 61.6% 2026-11-11 0110
LMArena text/longer_query 1,421 ±3.07 1,420 ±3 32.1% 2026-11-11 0110

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

A Language: 繁體中文 1,439 [1,417–1,460] Percentile 80 · #44 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,512 ±15 1,463 ±12 90.7% 2026-11-11 —

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

B Language: English 1,425 [1,419–1,430] Percentile 76 · #66 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,448 ±2.73 1,439 ±3 93.9% 2026-11-11 0110

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: 日本語 1,391 [1,369–1,412] Percentile 44 · #71 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,378 ±16 1,410 ±12 90.7% 2026-11-11 0110

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

B Language: 한국어 1,422 [1,405–1,438] Percentile 69 · #43 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,407 ±12 1,441 ±9 92.1% 2026-11-11 0110

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

A Language: Polski 1,452 [1,428–1,475] Percentile 88 · #17 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,485 ±16 1,480 ±13 90.0% 2026-11-11 —

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

B Language: Русский 1,432 [1,424–1,439] Percentile 77 · #54 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,445 ±4.45 1,447 ±4 93.7% 2026-11-11 0110

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 2026-11
ERNIE 5.0 (0110) 1,406 B

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: ERNIE 5.0 (0110)

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