Skip to content
fedi.software

granite-3.1-8b-instruct in fedi-index

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

fedi-index · General

D 1,163 ±7

Percentile 20 · #236 · provisional

People prefer / Solves tasks

1,160 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,163 [1,156–1,170] Percentile 20 · #236 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,149 ±5.57 1,150 ±6 32.8% 2026-10-02 —
LMArena text/hard_prompts 1,145 ±9.91 1,165 ±9 27.5% 2026-10-02 —
LMArena text/instruction_following 1,131 ±8.29 1,158 ±8 14.6% 2026-10-02 —
LMArena text/multi_turn 1,108 ±13 1,134 ±12 5.7% 2026-10-02 —
LMArena text/longer_query 1,162 ±14 1,178 ±13 5.4% 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 Coding 1,192 [1,173–1,212] Percentile 21 · #219 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,186 ±13 1,191 ±12 85.8% 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 1,164 [1,142–1,186] Percentile 18 · #208 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,152 ±14 1,155 ±14 81.3% 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 1,165 [1,147–1,183] Percentile 21 · #211 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,129 ±13 1,151 ±14 58.5% 2026-10-02 —
LMArena text/longer_query 1,162 ±14 1,178 ±13 31.4% 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: English 1,168 [1,154–1,182] Percentile 22 · #213 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,189 ±7.07 1,165 ±8 92.8% 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 1,137 [1,114–1,160] Percentile 8 · #215 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,092 ±14 1,130 ±13 90.2% 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
granite-3.1-8b-instruct 1,163 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: granite-3.1-8b-instruct

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