Skip to content
fedi.software

granite-3.0-2b-instruct in fedi-index

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

fedi-index · General

D 1,107 ±5

Percentile 12 · #258 · provisional

People prefer / Solves tasks

1,100 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,107 [1,102–1,112] Percentile 12 · #258 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,080 ±4.19 1,080 ±4 28.2% 2026-10-02 —
LMArena text/hard_prompts 1,073 ±7.36 1,100 ±7 25.4% 2026-10-02 —
LMArena text/instruction_following 1,056 ±6.21 1,087 ±6 13.2% 2026-10-02 —
LMArena text/expert 1,064 ±14 1,120 ±12 9.4% 2026-10-02 —
LMArena text/multi_turn 1,053 ±9.68 1,084 ±9 5.7% 2026-10-02 —
LMArena text/longer_query 1,070 ±12 1,093 ±11 4.8% 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 Coding 1,117 [1,103–1,130] Percentile 11 · #247 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,090 ±8.80 1,105 ±8 88.3% 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 Math 1,133 [1,118–1,149] Percentile 14 · #219 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,117 ±9.63 1,122 ±9 85.3% 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 1,086 [1,072–1,101] Percentile 9 · #245 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,046 ±11 1,067 ±11 61.5% 2026-10-02 —
LMArena text/longer_query 1,070 ±12 1,093 ±11 29.7% 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: 繁體中文 1,119 [1,102–1,136] Percentile 10 · #202 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,070 ±12 1,112 ±9 92.1% 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 Language: English 1,099 [1,088–1,110] Percentile 12 · #241 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,119 ±5.80 1,092 ±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

D Language: Русский 1,097 [1,081–1,113] Percentile 5 · #223 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,045 ±9.76 1,088 ±9 92.3% 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-3.0-2b-instruct 1,107 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-3.0-2b-instruct

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