Skip to content
fedi.software

GLM 5 in fedi-index

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

fedi-index · General

B 1,412 ±6

Percentile 75 · #75

People prefer / Solves tasks

1,428 / 1,390

Human votes vs benchmarks, Elo-eq

Value

+23

$1.55 per 1M tokens, median of 30 providers · vendor $1.55

On your hardware

Does not fit the reference setups.

Score decomposition

B General 1,412 [1,406–1,418] Percentile 75 · #75 · components: 8
Source Component Value Elo-eq Weight Measured Variant
Epoch AI eci 146 ±0.99 1,405 ±8 37.8% 2026-02-11 —
LMArena text/overall 1,446 ±2.16 1,446 ±2 15.7% 2026-10-02 —
LMArena text/hard_prompts 1,452 ±2.63 1,442 ±2 15.6% 2026-10-02 —
LMArena text/instruction_following 1,428 ±3.34 1,439 ±3 7.7% 2026-10-02 —
LMArena text/expert 1,455 ±5.93 1,439 ±5 7.2% 2026-10-02 —
LMArena text/longer_query 1,446 ±3.22 1,444 ±3 3.8% 2026-10-02 —
LMArena text/multi_turn 1,456 ±4.52 1,450 ±4 3.7% 2026-10-02 —
Epoch AI gpqa_diamond decay ×0.26 0.88 ±0.02 1,448 ±11 1.4% 2026-02-12 —

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 1,415 [1,411–1,419] Percentile 75 · #71 · components: 3
Source Component Value Elo-eq Weight Measured Variant
LMArena webdev/overall 1,434 ±4.15 1,431 ±1 40.0% 2026-10-01 —
LMArena text/coding 1,461 ±3.67 1,436 ±3 38.4% 2026-10-02 —
Epoch AI swe_bench_verified decay ×0.37 0.72 ±0.02 1,443 ±11 13.2% 2026-02-15 —

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 Agents 1,388 [1,380–1,396] Percentile 7 · #53 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
τ²-bench (Sierra) tau2/banking_knowledge decay ×0.76 0.10 ±0.03 1,430 ±5 81.4% 2026-02-27 enabled

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 1,401 [1,390–1,413] Percentile 73 · #70 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,440 ±7.19 1,431 ±7 86.9% 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

A Writing 1,444 [1,438–1,450] Percentile 84 · #44 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,439 ±4.56 1,468 ±5 61.4% 2026-10-02 —
LMArena text/longer_query 1,446 ±3.22 1,444 ±3 32.3% 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: 繁體中文 1,445 [1,435–1,455] Percentile 86 · #31 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,511 ±6.88 1,462 ±6 93.4% 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: Deutsch 1,420 [1,399–1,440] Percentile 68 · #46 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/german 1,445 ±13 1,441 ±11 91.0% 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

A Language: English 1,434 [1,429–1,440] Percentile 85 · #42 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,458 ±2.95 1,450 ±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 1,429 [1,414–1,444] Percentile 76 · #37 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,453 ±9.12 1,448 ±8 92.4% 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 [1,401–1,436] Percentile 60 · #55 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,455 ±10 1,438 ±10 91.9% 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: 한국어 1,432 [1,414–1,449] Percentile 79 · #29 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/korean 1,422 ±13 1,452 ±10 91.8% 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

B Language: Polski 1,418 [1,400–1,436] Percentile 64 · #48 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,436 ±12 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: Русский 1,424 [1,416–1,433] Percentile 76 · #57 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,436 ±5.07 1,439 ±5 93.6% 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

History

fedi-index by month
The same in a table
Model 2026-10
GLM 5 1,412 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: GLM 5

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