Skip to content
fedi.software

Grok 4.20 in fedi-index

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

fedi-index · General

A 1,425 ±8

Percentile 81 · #56

People prefer / Solves tasks

1,419 / 1,432

Human votes vs benchmarks, Elo-eq

Value

+33

$1.77 per 1M tokens, median of 3 providers

On your hardware

Closed weights: cloud only.

Score decomposition

A General 1,425 [1,417–1,433] Percentile 81 · #56 · components: 7
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 152 ±1.30 1,453 ±10 38.7% 2026-02-17 —
LMArena text/overall 1,444 ±2.32 1,444 ±2 15.8% 2026-10-02 —
LMArena text/hard_prompts 1,441 ±2.78 1,432 ±2 15.8% 2026-10-02 —
LMArena text/instruction_following 1,415 ±3.55 1,427 ±3 7.7% 2026-10-02 —
LMArena text/expert 1,428 ±6.29 1,418 ±5 7.3% 2026-10-02 —
LMArena text/longer_query 1,427 ±3.45 1,426 ±3 3.9% 2026-10-02 —
LMArena text/multi_turn 1,451 ±4.77 1,445 ±4 3.7% 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

B Coding 1,401 [1,395–1,407] Percentile 68 · #90 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,447 ±3.83 1,423 ±3 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

B Math 1,396 [1,384–1,408] Percentile 68 · #83 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,433 ±7.35 1,425 ±7 86.8% 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 Search 1,417 [1,411–1,423] Percentile 47 · #18 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena search/overall 1,189 ±3.08 1,431 ±3 93.9% 2026-08-24 —

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 1,437 [1,430–1,443] Percentile 82 · #49 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,438 ±4.92 1,467 ±5 61.1% 2026-10-02 —
LMArena text/longer_query 1,427 ±3.45 1,426 ±3 32.5% 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

B Language: 繁體中文 1,418 [1,407–1,429] Percentile 71 · #66 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,475 ±7.46 1,434 ±6 93.3% 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

A Language: Deutsch 1,433 [1,412–1,454] Percentile 82 · #27 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,463 ±14 1,457 ±12 90.7% 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

A Language: English 1,427 [1,421–1,433] Percentile 80 · #55 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,451 ±3.09 1,442 ±3 93.9% 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

B Language: Español 1,416 [1,400–1,433] Percentile 62 · #57 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,439 ±9.94 1,434 ±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

B Language: Français 1,418 [1,400–1,436] Percentile 59 · #56 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,455 ±11 1,438 ±10 91.7% 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

B Language: 한국어 1,426 [1,407–1,446] Percentile 73 · #37 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,416 ±14 1,448 ±11 91.3% 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

B Language: Polski 1,415 [1,396–1,433] Percentile 57 · #57 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,432 ±12 1,434 ±10 91.6% 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

A Language: Русский 1,434 [1,425–1,443] Percentile 81 · #45 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,448 ±5.42 1,450 ±5 93.5% 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

History

fedi-index by month
The same in a table
Model 2026-10
Grok 4.20 1,425 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: Grok 4.20

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