Skip to content
fedi.software

vicuna-13b in fedi-index

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

fedi-index · General

D 1,078 ±4

Percentile 6 · #274 · provisional

People prefer / Solves tasks

1,070 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,078 [1,074–1,082] Percentile 6 · #274 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,058 ±3.36 1,058 ±3 27.8% 2026-10-02 —
LMArena text/hard_prompts 1,024 ±5.36 1,055 ±5 26.5% 2026-10-02 —
LMArena text/instruction_following 1,035 ±4.83 1,067 ±5 13.4% 2026-10-02 —
LMArena text/expert 994 ±16 1,062 ±13 8.4% 2026-10-02 —
LMArena text/multi_turn 1,031 ±7.12 1,064 ±6 6.2% 2026-10-02 —
LMArena text/longer_query 1,047 ±11 1,071 ±10 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 1,076 [1,066–1,087] Percentile 7 · #259 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,041 ±6.96 1,061 ±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

D Math 1,060 [1,048–1,071] Percentile 5 · #242 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,030 ±6.99 1,038 ±7 87.0% 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 Writing 1,086 [1,076–1,096] Percentile 8 · #246 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,058 ±6.43 1,079 ±7 65.7% 2026-10-02 —
LMArena text/longer_query 1,047 ±11 1,071 ±10 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 1,096 [1,082–1,110] Percentile 6 · #210 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,039 ±9.86 1,088 ±8 92.6% 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: English 1,060 [1,053–1,068] Percentile 6 · #256 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,080 ±3.81 1,050 ±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 1,096 [1,074–1,118] Percentile 4 · #225 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,042 ±14 1,085 ±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

History

fedi-index by month
The same in a table
Model 2026-10
vicuna-13b 1,078 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: vicuna-13b

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