Skip to content
fedi.software

vicuna-7b in fedi-index

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

fedi-index · General

D 1,052 ±6

Percentile 4 · #280 · provisional

People prefer / Solves tasks

1,041 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,052 [1,046–1,058] Percentile 4 · #280 · components: 4 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,031 ±4.63 1,031 ±5 34.6% 2026-10-02 —
LMArena text/hard_prompts 995 ±8.49 1,029 ±8 30.0% 2026-10-02 —
LMArena text/instruction_following 994 ±7.08 1,028 ±7 15.8% 2026-10-02 —
LMArena text/multi_turn 988 ±11 1,025 ±10 6.7% 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 1,056 [1,039–1,073] Percentile 4 · #266 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,010 ±11 1,034 ±10 86.8% 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 Math 1,035 [1,017–1,052] Percentile 4 · #246 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 994 ±11 1,003 ±10 84.3% 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 Writing 1,054 [1,037–1,071] Percentile 5 · #254 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,021 ±9.10 1,041 ±9 92.0% 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: 繁體中文 1,056 [1,032–1,079] Percentile 2 · #219 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 979 ±17 1,039 ±13 90.0% 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 1,032 [1,022–1,041] Percentile 4 · #261 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,051 ±5.04 1,020 ±5 93.4% 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

History

fedi-index by month
The same in a table
Model 2026-10
vicuna-7b 1,052 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-7b

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