Skip to content
fedi.software

gemma-2-9b-it-simpo in fedi-index

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

fedi-index · General

D 1,216 ±4

Percentile 24 · #222 · provisional

People prefer / Solves tasks

1,217 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,216 [1,212–1,221] Percentile 24 · #222 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,227 ±3.49 1,227 ±4 27.7% 2026-10-02 —
LMArena text/hard_prompts 1,196 ±5.77 1,211 ±5 26.1% 2026-10-02 —
LMArena text/instruction_following 1,191 ±5.07 1,215 ±5 13.2% 2026-10-02 —
LMArena text/expert 1,154 ±15 1,194 ±12 8.8% 2026-10-02 —
LMArena text/multi_turn 1,220 ±7.37 1,235 ±7 6.1% 2026-10-02 —
LMArena text/longer_query 1,226 ±9.64 1,238 ±9 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 1,196 [1,184–1,208] Percentile 22 · #218 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,191 ±7.53 1,195 ±7 88.9% 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 1,179 [1,166–1,191] Percentile 21 · #202 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,173 ±7.70 1,175 ±7 86.6% 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 1,252 [1,241–1,262] Percentile 30 · #189 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,239 ±7.42 1,264 ±8 63.3% 2026-10-02 —
LMArena text/longer_query 1,226 ±9.64 1,238 ±9 29.2% 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: 繁體中文 1,232 [1,217–1,248] Percentile 20 · #178 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,225 ±11 1,235 ±8 92.4% 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: Deutsch 1,241 [1,217–1,265] Percentile 19 · #117 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,218 ±16 1,246 ±14 89.7% 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

C Language: English 1,220 [1,212–1,229] Percentile 27 · #199 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,242 ±4.42 1,222 ±5 93.6% 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 1,246 [1,232–1,260] Percentile 20 · #188 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,225 ±8.61 1,249 ±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

History

fedi-index by month
The same in a table
Model 2026-10
gemma-2-9b-it-simpo 1,216 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-2-9b-it-simpo

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