Skip to content
fedi.software

vicuna-33b in fedi-index

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

fedi-index · General

D 1,110 ±4

Percentile 13 · #255 · provisional

People prefer / Solves tasks

1,103 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,110 [1,106–1,113] Percentile 13 · #255 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,105 ±3.12 1,105 ±3 27.4% 2026-10-02 —
LMArena text/hard_prompts 1,067 ±5.05 1,094 ±5 26.2% 2026-10-02 —
LMArena text/instruction_following 1,065 ±4.54 1,096 ±4 13.2% 2026-10-02 —
LMArena text/expert 1,029 ±14 1,091 ±11 9.2% 2026-10-02 —
LMArena text/multi_turn 1,080 ±6.58 1,109 ±6 6.2% 2026-10-02 —
LMArena text/longer_query 1,029 ±9.67 1,054 ±9 5.2% 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 1,106 [1,096–1,116] Percentile 9 · #253 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,078 ±6.43 1,094 ±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 1,093 [1,083–1,104] Percentile 9 · #233 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,071 ±6.40 1,077 ±6 87.3% 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 1,137 [1,127–1,146] Percentile 17 · #222 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,125 ±6.06 1,147 ±6 75.5% 2026-10-02 —
LMArena text/longer_query outlier 1,029 ±9.67 1,054 ±9 16.2% 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 1,093 [1,080–1,106] Percentile 5 · #211 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,036 ±8.78 1,085 ±7 92.9% 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: Deutsch 1,118 [1,094–1,140] Percentile 7 · #134 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,059 ±15 1,108 ±13 90.1% 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 Language: English 1,112 [1,105–1,120] Percentile 14 · #234 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,133 ±3.69 1,106 ±4 93.8% 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: Русский 1,128 [1,110–1,146] Percentile 7 · #217 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,083 ±11 1,122 ±10 91.7% 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

History

fedi-index by month
The same in a table
Model 2026-10
vicuna-33b 1,110 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-33b

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