Skip to content
fedi.software

Gemini 4 Argon (High) in fedi-index

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

fedi-index · General

A 1,490 ±5

Percentile 99 · #4 · provisional

People prefer / Solves tasks

1,509 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

A General 1,490 [1,485–1,494] Percentile 99 · #4 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,533 ±4.48 1,534 ±4 27.2% 2026-10-02 high
LMArena text/hard_prompts 1,548 ±5.56 1,529 ±5 26.7% 2026-10-02 high
LMArena text/instruction_following 1,537 ±7.36 1,543 ±7 12.2% 2026-10-02 high
LMArena text/expert 1,549 ±13 1,516 ±11 9.8% 2026-10-02 high
LMArena text/longer_query 1,548 ±6.99 1,539 ±6 6.2% 2026-10-02 high
LMArena text/multi_turn 1,558 ±12 1,542 ±11 4.8% 2026-10-02 high

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

A Coding 1,474 [1,468–1,480] Percentile 99 · #4 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,680 ±6.77 1,501 ±2 49.7% 2026-10-01 high
LMArena text/coding 1,547 ±8.75 1,513 ±8 39.8% 2026-10-02 high

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

A Agents 1,462 [1,454–1,470] Percentile 82 · #11 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena agent/overall 0.08 ±0.01 1,492 ±5 89.7% 2026-10-02 high

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

A Writing 1,526 [1,514–1,538] Percentile 100 · #1 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,531 ±9.86 1,562 ±10 57.3% 2026-10-02 high
LMArena text/longer_query 1,548 ±6.99 1,539 ±6 34.9% 2026-10-02 high

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

A Language: 繁體中文 1,507 [1,484–1,530] Percentile 100 · #1 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,609 ±16 1,540 ±13 90.3% 2026-10-02 high

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

A Language: English 1,511 [1,497–1,524] Percentile 100 · #1 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,539 ±7.05 1,535 ±7 92.8% 2026-10-02 high

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

A Language: Русский 1,506 [1,487–1,524] Percentile 100 · #1 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,541 ±12 1,534 ±10 91.5% 2026-10-02 high

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 4 Argon (High) 1,490 A

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 4 Argon (High)

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