Skip to content
fedi.software

Gemini Advanced (0514) in fedi-index

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

fedi-index · General

C 1,259 ±3

Percentile 30 · #209 · provisional

People prefer / Solves tasks

1,262 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,259 [1,256–1,262] Percentile 30 · #209 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,279 ±2.60 1,279 ±3 26.0% 2026-11-11 0514
LMArena text/hard_prompts 1,248 ±3.68 1,258 ±3 25.6% 2026-11-11 0514
LMArena text/instruction_following 1,253 ±3.42 1,274 ±3 12.8% 2026-11-11 0514
LMArena text/expert 1,215 ±7.31 1,243 ±6 11.6% 2026-11-11 0514
LMArena text/multi_turn 1,269 ±4.87 1,280 ±4 6.2% 2026-11-11 0514
LMArena text/longer_query 1,253 ±5.29 1,263 ±5 6.0% 2026-11-11 0514

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 1,246 [1,239–1,253] Percentile 26 · #212 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,255 ±4.54 1,252 ±4 88.2% 2026-11-11 0514

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 1,262 [1,254–1,270] Percentile 31 · #176 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,272 ±4.85 1,270 ±5 87.9% 2026-11-11 0514

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 1,288 [1,282–1,295] Percentile 36 · #169 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,284 ±5.00 1,310 ±5 62.2% 2026-11-11 0514
LMArena text/longer_query 1,253 ±5.29 1,263 ±5 31.3% 2026-11-11 0514

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: 繁體中文 1,269 [1,261–1,278] Percentile 26 · #163 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,274 ±5.73 1,274 ±4 93.6% 2026-11-11 0514

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 1,287 [1,273–1,302] Percentile 24 · #111 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,275 ±8.98 1,294 ±8 92.7% 2026-11-11 0514

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 1,259 [1,253–1,265] Percentile 32 · #182 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,282 ±3.07 1,263 ±3 93.9% 2026-11-11 0514

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: Español 1,248 [1,227–1,268] Percentile 8 · #138 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,242 ±13 1,252 ±12 90.9% 2026-11-11 0514

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: Français 1,292 [1,270–1,313] Percentile 14 · #123 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,306 ±13 1,301 ±12 90.6% 2026-11-11 0514

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: 日本語 1,301 [1,286–1,315] Percentile 21 · #101 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,242 ±11 1,309 ±8 92.6% 2026-11-11 0514

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: 한국어 1,300 [1,285–1,315] Percentile 18 · #113 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,232 ±11 1,308 ±8 92.5% 2026-11-11 0514

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: Русский 1,295 [1,286–1,304] Percentile 30 · #162 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,282 ±5.31 1,301 ±5 93.6% 2026-11-11 0514

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 2026-11
Gemini Advanced (0514) 1,259 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: Gemini Advanced (0514)

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