Skip to content
fedi.software

yi-34b-chat in fedi-index

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

fedi-index · General

D 1,135 ±4

Percentile 16 · #247 · provisional

People prefer / Solves tasks

1,131 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,135 [1,131–1,139] Percentile 16 · #247 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,128 ±3.45 1,128 ±4 27.3% 2026-10-02 —
LMArena text/hard_prompts 1,104 ±5.36 1,127 ±5 26.0% 2026-10-02 —
LMArena text/instruction_following 1,091 ±4.93 1,120 ±5 13.1% 2026-10-02 —
LMArena text/expert 1,061 ±13 1,118 ±10 9.7% 2026-10-02 —
LMArena text/multi_turn 1,113 ±7.55 1,138 ±7 5.9% 2026-10-02 —
LMArena text/longer_query 1,094 ±9.13 1,114 ±8 5.4% 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 Coding 1,133 [1,122–1,143] Percentile 14 · #239 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,112 ±6.61 1,124 ±6 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 Math 1,129 [1,118–1,140] Percentile 13 · #221 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,114 ±6.74 1,118 ±6 87.1% 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

D Writing 1,131 [1,121–1,141] Percentile 15 · #227 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,108 ±6.98 1,130 ±7 63.4% 2026-10-02 —
LMArena text/longer_query 1,094 ±9.13 1,114 ±8 29.4% 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: 繁體中文 1,196 [1,183–1,209] Percentile 14 · #191 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,175 ±9.24 1,196 ±7 92.8% 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: Deutsch 1,105 [1,080–1,130] Percentile 4 · #138 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,042 ±16 1,093 ±14 89.4% 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: English 1,138 [1,130–1,146] Percentile 18 · #223 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,159 ±4.03 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: Русский 1,101 [1,083–1,118] Percentile 5 · #222 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,050 ±11 1,092 ±10 91.9% 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

History

fedi-index by month
The same in a table
Model 2026-10
yi-34b-chat 1,135 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: yi-34b-chat

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