Skip to content
fedi.software

ChatGLM2 6B in fedi-index

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

fedi-index · General

D 975 ±12

Percentile 2 · #290

People prefer / Solves tasks

968 / 1,022

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 975 [964–987] Percentile 2 · #290 · components: 5
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 939 ±6.85 939 ±7 34.4% 2026-11-11 —
LMArena text/hard_prompts 917 ±13 959 ±12 25.3% 2026-11-11 —
LMArena text/instruction_following 902 ±11 941 ±11 13.7% 2026-11-11 —
Epoch AI eci 73.99 ±7.41 838 ±58 7.1% 2023-06-24 —
LMArena text/multi_turn 902 ±16 947 ±15 5.2% 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

D Writing 984 [960–1,008] Percentile 3 · #257 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 941 ±13 959 ±14 89.7% 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

D Language: English 957 [943–972] Percentile 3 · #261 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 973 ±7.60 938 ±8 92.6% 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
975 980 985 990 995 2026-10 2026-11 ChatGLM2 6B · 2026-10 · 990ChatGLM2 6B · 2026-11 · 975 ChatGLM2 6B
The same in a table
Model 2026-102026-11
ChatGLM2 6B 990975 D

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: ChatGLM2 6B

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