Skip to content
fedi.software

gemma-1.1-7b-it in fedi-index

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

fedi-index · General

D 1,106 ±3

Percentile 12 · #259 · provisional

People prefer / Solves tasks

1,099 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,106 [1,102–1,109] Percentile 12 · #259 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,094 ±3.06 1,094 ±3 26.4% 2026-10-02 —
LMArena text/hard_prompts 1,071 ±4.34 1,097 ±4 25.7% 2026-10-02 —
LMArena text/instruction_following 1,057 ±4.04 1,088 ±4 12.9% 2026-10-02 —
LMArena text/expert 1,039 ±8.98 1,100 ±7 11.1% 2026-10-02 —
LMArena text/multi_turn 1,040 ±5.96 1,072 ±5 6.1% 2026-10-02 —
LMArena text/longer_query 1,056 ±6.41 1,079 ±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 1,110 [1,102–1,118] Percentile 10 · #251 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,084 ±5.26 1,099 ±5 89.7% 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 Math 1,123 [1,114–1,133] Percentile 11 · #226 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,107 ±5.77 1,112 ±6 87.6% 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 Writing 1,088 [1,080–1,096] Percentile 9 · #244 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,059 ±5.96 1,080 ±6 62.1% 2026-10-02 —
LMArena text/longer_query 1,056 ±6.41 1,079 ±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 1,111 [1,101–1,120] Percentile 7 · #207 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,060 ±6.39 1,104 ±5 93.5% 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 Language: Deutsch 1,112 [1,094–1,129] Percentile 5 · #137 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,054 ±11 1,104 ±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

D Language: English 1,103 [1,096–1,110] Percentile 13 · #238 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,124 ±3.65 1,096 ±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: Español 1,089 [1,062–1,116] Percentile 0 · #149 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,049 ±17 1,074 ±16 88.5% 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 Language: Français 1,093 [1,066–1,119] Percentile 2 · #133 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,064 ±17 1,079 ±15 88.7% 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: 日本語 1,115 [1,094–1,135] Percentile 4 · #123 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 971 ±15 1,106 ±12 91.0% 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: 한국어 1,128 [1,111–1,146] Percentile 4 · #131 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 987 ±13 1,122 ±10 91.8% 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 1,096 [1,086–1,107] Percentile 3 · #226 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,046 ±6.42 1,088 ±6 93.3% 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

History

fedi-index by month
The same in a table
Model 2026-10
gemma-1.1-7b-it 1,106 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: gemma-1.1-7b-it

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