Skip to content
fedi.software

GPT-5.2 Chat in fedi-index

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

fedi-index · General

B 1,408 ±2

Percentile 70 · #90 · provisional

People prefer / Solves tasks

1,420 / —

Human votes vs benchmarks, Elo-eq

Value

-15

$4.81 per 1M tokens, median of 1 providers

On your hardware

Closed weights: cloud only.

Score decomposition

B General 1,408 [1,406–1,410] Percentile 70 · #90 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,438 ±2.04 1,438 ±2 25.7% 2026-11-11 —
LMArena text/hard_prompts 1,445 ±2.50 1,436 ±2 25.6% 2026-11-11 —
LMArena text/instruction_following 1,417 ±3.16 1,429 ±3 12.6% 2026-11-11 —
LMArena text/expert 1,437 ±5.53 1,425 ±4 12.0% 2026-11-11 —
LMArena text/longer_query 1,427 ±3.05 1,426 ±3 6.3% 2026-11-11 —
LMArena text/multi_turn 1,458 ±3.96 1,452 ±4 6.2% 2026-11-11 —

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 1,398 [1,392–1,403] Percentile 63 · #106 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,447 ±3.42 1,423 ±3 88.5% 2026-11-11 —

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 1,397 [1,386–1,408] Percentile 65 · #91 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,434 ±6.65 1,426 ±6 87.1% 2026-11-11 —

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 Vision 1,432 [1,428–1,436] Percentile 66 · #38 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,268 ±3.28 1,446 ±3 63.2% 2026-11-09 —
LMArena vision/ocr 1,275 ±3.44 1,447 ±3 15.6% 2026-11-09 —
LMArena vision/diagram 1,285 ±5.11 1,450 ±4 15.0% 2026-11-09 —

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 Writing 1,413 [1,408–1,419] Percentile 70 · #80 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,400 ±4.29 1,428 ±4 61.5% 2026-11-11 —
LMArena text/longer_query 1,427 ±3.05 1,426 ±3 32.2% 2026-11-11 —

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 1,407 [1,398–1,416] Percentile 59 · #90 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,460 ±6.34 1,421 ±5 93.5% 2026-11-11 —

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: Deutsch 1,422 [1,402–1,442] Percentile 70 · #44 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,447 ±13 1,443 ±11 91.2% 2026-11-11 —

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: English 1,422 [1,417–1,428] Percentile 73 · #73 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,446 ±2.81 1,436 ±3 93.9% 2026-11-11 —

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: Español 1,410 [1,395–1,426] Percentile 50 · #76 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,431 ±9.05 1,428 ±8 92.4% 2026-11-11 —

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: Français 1,405 [1,389–1,422] Percentile 45 · #78 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,439 ±10 1,423 ±9 92.1% 2026-11-11 —

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 1,410 [1,392–1,428] Percentile 60 · #55 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,392 ±13 1,429 ±10 91.7% 2026-11-11 —

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 1,416 [1,399–1,434] Percentile 56 · #58 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,433 ±11 1,435 ±10 91.9% 2026-11-11 —

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: Русский 1,428 [1,420–1,435] Percentile 76 · #56 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,440 ±4.72 1,443 ±4 93.7% 2026-11-11 —

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
GPT-5.2 Chat 1,408 B

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: GPT-5.2 Chat

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