Skip to content
fedi.software

GLM 4.5V in fedi-index

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

fedi-index · General

C 1,316 ±5

Percentile 37 · #184 · provisional

People prefer / Solves tasks

1,323 / —

Human votes vs benchmarks, Elo-eq

Value

-60

$0.90 per 1M tokens, median of 12 providers · vendor $0.90

On your hardware

  • GPU 24 GB #22 · Q4_K_M · ≈9 tok/s
  • 128 GB unified memory #31 · Q4_K_M · ≈16 tok/s

Score decomposition

C General 1,316 [1,311–1,320] Percentile 37 · #184 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,333 ±4.30 1,333 ±4 31.4% 2026-10-02 —
LMArena text/hard_prompts 1,335 ±6.13 1,336 ±6 29.9% 2026-10-02 —
LMArena text/instruction_following 1,311 ±8.06 1,329 ±8 13.5% 2026-10-02 —
LMArena text/longer_query 1,305 ±9.08 1,312 ±8 6.4% 2026-10-02 —
LMArena text/multi_turn 1,333 ±10 1,338 ±9 6.1% 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

C Coding 1,318 [1,304–1,333] Percentile 35 · #182 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,347 ±9.50 1,334 ±8 87.9% 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

D Vision 1,329 [1,321–1,337] Percentile 22 · #88 · components: 3 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena vision/overall 1,154 ±5.93 1,343 ±5 67.7% 2026-10-02 —
LMArena vision/ocr 1,150 ±8.63 1,327 ±8 14.6% 2026-10-02 —
LMArena vision/diagram 1,151 ±15 1,331 ±14 10.6% 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

C Writing 1,308 [1,293–1,322] Percentile 39 · #164 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,295 ±12 1,321 ±12 56.5% 2026-10-02 —
LMArena text/longer_query 1,305 ±9.08 1,312 ±8 34.8% 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 Language: English 1,338 [1,325–1,350] Percentile 43 · #157 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,362 ±6.46 1,348 ±7 93.0% 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

C Language: Русский 1,305 [1,282–1,327] Percentile 31 · #162 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,299 ±14 1,316 ±13 90.4% 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

History

fedi-index by month
The same in a table
Model 2026-10
GLM 4.5V 1,316 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: GLM 4.5V

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