Skip to content
fedi.software

gemini-1.5-pro-002 in fedi-index

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

fedi-index · General

C 1,296 ±8

Percentile 35 · #189

People prefer / Solves tasks

1,302 / 1,285

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,296 [1,288–1,303] Percentile 35 · #189 · components: 8
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 132 ±1.52 1,294 ±12 32.0% 2024-09-24 —
LMArena text/overall 1,319 ±1.72 1,319 ±2 17.2% 2026-10-02 —
LMArena text/hard_prompts 1,296 ±2.83 1,301 ±3 17.0% 2026-10-02 —
LMArena text/instruction_following 1,297 ±2.54 1,316 ±2 8.5% 2026-10-02 —
LMArena text/expert 1,278 ±5.60 1,295 ±5 8.0% 2026-10-02 —
LMArena text/multi_turn 1,296 ±3.53 1,305 ±3 4.2% 2026-10-02 —
LMArena text/longer_query 1,308 ±3.64 1,314 ±3 4.2% 2026-10-02 —
Epoch AI gpqa_diamond decay ×0.26 0.57 ±0.03 1,306 ±13 1.3% 2025-01-27 —

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 1,279 [1,273–1,284] Percentile 30 · #184 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,294 ±3.47 1,287 ±3 90.2% 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 Math 1,299 [1,292–1,305] Percentile 35 · #165 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,315 ±3.76 1,311 ±4 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 Vision 1,340 [1,333–1,348] Percentile 25 · #85 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,161 ±4.61 1,350 ±4 93.7% 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 Writing 1,336 [1,331–1,341] Percentile 46 · #146 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,333 ±3.75 1,360 ±4 62.3% 2026-10-02 —
LMArena text/longer_query 1,308 ±3.64 1,314 ±3 31.5% 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

C Language: 繁體中文 1,312 [1,304–1,319] Percentile 30 · #156 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,331 ±5.05 1,319 ±4 93.7% 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: Deutsch 1,297 [1,283–1,310] Percentile 24 · #109 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,286 ±8.60 1,304 ±7 92.8% 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

C Language: English 1,300 [1,296–1,304] Percentile 36 · #174 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,322 ±2.26 1,306 ±2 94.0% 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: Español 1,304 [1,280–1,328] Percentile 11 · #133 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,310 ±15 1,316 ±14 89.6% 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: Français 1,286 [1,263–1,310] Percentile 12 · #119 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,300 ±15 1,295 ±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

C Language: 日本語 1,336 [1,324–1,348] Percentile 26 · #95 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,292 ±9.08 1,346 ±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: 한국어 1,345 [1,329–1,362] Percentile 24 · #103 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,297 ±12 1,357 ±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

C Language: Русский 1,327 [1,320–1,333] Percentile 32 · #158 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,320 ±3.92 1,335 ±4 93.8% 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

History

fedi-index by month
The same in a table
Model 2026-10
gemini-1.5-pro-002 1,296 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-1.5-pro-002

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