Skip to content
fedi.software

granite-3.1-2b-instruct in fedi-index

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

fedi-index · General

D 1,151 ±7

Percentile 19 · #238 · provisional

People prefer / Solves tasks

1,148 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,151 [1,145–1,158] Percentile 19 · #238 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,127 ±5.63 1,127 ±6 32.6% 2026-10-02 —
LMArena text/hard_prompts 1,138 ±9.62 1,158 ±9 27.8% 2026-10-02 —
LMArena text/instruction_following 1,116 ±8.27 1,144 ±8 14.6% 2026-10-02 —
LMArena text/longer_query 1,155 ±13 1,172 ±12 5.5% 2026-10-02 —
LMArena text/multi_turn 1,099 ±14 1,126 ±12 5.5% 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 Coding 1,164 [1,145–1,183] Percentile 17 · #230 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,149 ±12 1,158 ±11 86.1% 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 Math 1,169 [1,149–1,190] Percentile 19 · #206 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,159 ±13 1,162 ±13 82.2% 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 Writing 1,156 [1,138–1,175] Percentile 20 · #216 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,116 ±15 1,138 ±15 56.0% 2026-10-02 —
LMArena text/longer_query 1,155 ±13 1,172 ±12 33.5% 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: English 1,152 [1,138–1,166] Percentile 20 · #218 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,172 ±7.26 1,148 ±8 92.7% 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 1,114 [1,091–1,136] Percentile 6 · #220 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,063 ±14 1,104 ±13 90.3% 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
granite-3.1-2b-instruct 1,151 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-3.1-2b-instruct

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