Skip to content
fedi.software

dbrx-instruct-preview in fedi-index

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

fedi-index · General

D 1,139 ±3

Percentile 16 · #245 · provisional

People prefer / Solves tasks

1,135 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,139 [1,136–1,142] Percentile 16 · #245 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,119 ±3.09 1,119 ±3 26.3% 2026-10-02 —
LMArena text/hard_prompts 1,113 ±4.58 1,136 ±4 25.5% 2026-10-02 —
LMArena text/instruction_following 1,112 ±4.30 1,140 ±4 12.8% 2026-10-02 —
LMArena text/expert 1,076 ±8.26 1,130 ±7 11.4% 2026-10-02 —
LMArena text/multi_turn 1,111 ±5.96 1,137 ±5 6.1% 2026-10-02 —
LMArena text/longer_query 1,112 ±6.33 1,131 ±6 5.9% 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 Coding 1,148 [1,140–1,157] Percentile 16 · #233 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,132 ±5.54 1,142 ±5 89.6% 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 Math 1,155 [1,146–1,165] Percentile 16 · #213 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,145 ±5.85 1,148 ±6 87.5% 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

D Writing 1,133 [1,125–1,141] Percentile 16 · #224 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,104 ±5.90 1,126 ±6 62.1% 2026-10-02 —
LMArena text/longer_query 1,112 ±6.33 1,131 ±6 31.2% 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 1,116 [1,106–1,126] Percentile 9 · #203 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,068 ±6.67 1,110 ±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

D Language: Deutsch 1,115 [1,096–1,133] Percentile 6 · #136 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,057 ±12 1,107 ±10 91.6% 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 1,134 [1,126–1,141] Percentile 18 · #224 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,155 ±3.86 1,129 ±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: Español 1,101 [1,074–1,128] Percentile 1 · #147 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,064 ±17 1,088 ±16 88.6% 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: Français 1,117 [1,092–1,142] Percentile 3 · #131 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,095 ±16 1,107 ±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: 日本語 1,128 [1,107–1,148] Percentile 5 · #122 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 989 ±16 1,120 ±12 90.8% 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: 한국어 1,133 [1,112–1,154] Percentile 4 · #130 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 992 ±16 1,126 ±12 90.7% 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 1,123 [1,112–1,134] Percentile 7 · #218 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,078 ±6.62 1,117 ±6 93.2% 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

History

fedi-index by month
The same in a table
Model 2026-10
dbrx-instruct-preview 1,139 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: dbrx-instruct-preview

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