Skip to content
fedi.software

Gemma 7B IT in fedi-index

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

fedi-index · General

D 1,077 ±12

Percentile 7 · #275

People prefer / Solves tasks

1,069 / 1,100

Human votes vs benchmarks, Elo-eq

Value

-239

$0.15 per 1M tokens, median of 1 providers

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,077 [1,065–1,088] Percentile 7 · #275 · components: 7
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,056 ±4.86 1,056 ±5 23.2% 2026-11-11 —
LMArena text/hard_prompts 1,042 ±6.82 1,071 ±6 21.9% 2026-11-11 —
Epoch AI eci 103 ±3.72 1,069 ±29 18.6% 2024-02-21 —
LMArena text/instruction_following 1,017 ±6.49 1,050 ±6 11.0% 2026-11-11 —
LMArena text/expert 1,001 ±16 1,068 ±13 7.4% 2026-11-11 —
LMArena text/longer_query 1,021 ±11 1,047 ±11 4.3% 2026-11-11 —
LMArena text/multi_turn outlier 963 ±9.54 1,002 ±9 2.4% 2026-11-11 —

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 1,086 [1,073–1,098] Percentile 8 · #263 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,048 ±8.36 1,068 ±8 86.5% 2026-11-11 —

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 1,091 [1,078–1,105] Percentile 9 · #232 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,066 ±8.37 1,073 ±8 86.1% 2026-11-11 —

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 1,057 [1,045–1,070] Percentile 8 · #244 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,023 ±8.97 1,044 ±9 63.0% 2026-11-11 —
LMArena text/longer_query 1,021 ±11 1,047 ±11 28.9% 2026-11-11 —

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 [1,079–1,108] Percentile 6 · #206 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,036 ±10 1,084 ±8 92.6% 2026-11-11 —

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 1,070 [1,059–1,081] Percentile 9 · #246 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,090 ±5.65 1,061 ±6 93.2% 2026-11-11 —

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 1,055 [1,036–1,074] Percentile 2 · #226 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 993 ±12 1,041 ±11 91.4% 2026-11-11 —

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
1,075 1,080 1,085 1,090 1,095 2026-10 2026-11 Gemma 7B IT · 2026-10 · 1,091Gemma 7B IT · 2026-11 · 1,077 Gemma 7B IT
The same in a table
Model 2026-102026-11
Gemma 7B IT 1,0911,077 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 7B IT

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