Skip to content
fedi.software

Grok 2 (2024-08-13) in fedi-index

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

fedi-index · General

C 1,279 ±2

Percentile 32 · #203 · provisional

People prefer / Solves tasks

1,284 / —

Human votes vs benchmarks, Elo-eq

Value

-137

$4 per 1M tokens, median of 1 providers

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,279 [1,277–1,282] Percentile 32 · #203 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,305 ±1.87 1,305 ±2 25.8% 2026-11-11 2024-08-13
LMArena text/hard_prompts 1,272 ±2.83 1,279 ±3 25.5% 2026-11-11 2024-08-13
LMArena text/instruction_following 1,270 ±2.55 1,290 ±2 12.8% 2026-11-11 2024-08-13
LMArena text/expert 1,253 ±5.55 1,275 ±4 12.0% 2026-11-11 2024-08-13
LMArena text/multi_turn 1,290 ±3.62 1,299 ±3 6.2% 2026-11-11 2024-08-13
LMArena text/longer_query 1,276 ±3.68 1,285 ±3 6.2% 2026-11-11 2024-08-13

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 1,272 [1,266–1,277] Percentile 29 · #204 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,287 ±3.52 1,281 ±3 88.5% 2026-11-11 2024-08-13

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 1,272 [1,266–1,278] Percentile 33 · #172 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,283 ±3.72 1,281 ±4 88.3% 2026-11-11 2024-08-13

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 1,295 [1,290–1,301] Percentile 38 · #164 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,284 ±3.78 1,310 ±4 62.3% 2026-11-11 2024-08-13
LMArena text/longer_query 1,276 ±3.68 1,285 ±3 31.5% 2026-11-11 2024-08-13

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 1,281 [1,274–1,288] Percentile 27 · #161 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,289 ±4.86 1,286 ±4 93.8% 2026-11-11 2024-08-13

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: Deutsch 1,297 [1,284–1,310] Percentile 25 · #109 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,287 ±8.19 1,304 ±7 92.9% 2026-11-11 2024-08-13

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 1,298 [1,294–1,303] Percentile 37 · #169 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,321 ±2.32 1,304 ±2 94.0% 2026-11-11 2024-08-13

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 1,281 [1,260–1,301] Percentile 11 · #134 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,281 ±12 1,288 ±12 90.9% 2026-11-11 2024-08-13

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 1,301 [1,279–1,323] Percentile 14 · #122 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,318 ±13 1,311 ±12 90.5% 2026-11-11 2024-08-13

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 1,303 [1,291–1,315] Percentile 21 · #100 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,244 ±8.64 1,310 ±6 93.1% 2026-11-11 2024-08-13

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 1,303 [1,288–1,319] Percentile 19 · #111 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,237 ±11 1,311 ±8 92.4% 2026-11-11 2024-08-13

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 1,298 [1,291–1,304] Percentile 30 · #161 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,286 ±3.91 1,304 ±4 93.8% 2026-11-11 2024-08-13

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
Grok 2 (2024-08-13) 1,279 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: Grok 2 (2024-08-13)

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