Skip to content
fedi.software

ibm-granite-h-small in fedi-index

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

fedi-index · General

C 1,241 ±5

Percentile 27 · #214 · provisional

People prefer / Solves tasks

1,243 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,241 [1,236–1,246] Percentile 27 · #214 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,241 ±4.33 1,241 ±4 31.2% 2026-10-02 —
LMArena text/hard_prompts 1,240 ±5.81 1,250 ±5 30.1% 2026-10-02 —
LMArena text/instruction_following 1,220 ±7.87 1,243 ±8 13.5% 2026-10-02 —
LMArena text/longer_query 1,240 ±8.75 1,251 ±8 6.5% 2026-10-02 —
LMArena text/multi_turn 1,243 ±10 1,256 ±9 6.1% 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

C Coding 1,240 [1,226–1,254] Percentile 26 · #206 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,247 ±8.78 1,245 ±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

C Math 1,240 [1,216–1,264] Percentile 29 · #182 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,251 ±16 1,250 ±16 79.2% 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

C Writing 1,238 [1,224–1,252] Percentile 28 · #193 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,211 ±12 1,235 ±12 55.7% 2026-10-02 —
LMArena text/longer_query 1,240 ±8.75 1,251 ±8 35.7% 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 1,250 [1,227–1,273] Percentile 23 · #171 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,251 ±17 1,255 ±13 90.1% 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

C Language: English 1,244 [1,231–1,256] Percentile 28 · #196 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,266 ±6.33 1,247 ±7 93.0% 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: Русский 1,223 [1,199–1,246] Percentile 18 · #193 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,198 ±15 1,225 ±13 90.0% 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

History

fedi-index by month
The same in a table
Model 2026-10
ibm-granite-h-small 1,241 C

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: ibm-granite-h-small

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