Skip to content
fedi.software

OpenChat 3.5 (0106) in fedi-index

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

fedi-index · General

D 1,121 ±4

Percentile 15 · #252 · provisional

People prefer / Solves tasks

1,116 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,121 [1,117–1,126] Percentile 15 · #252 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,107 ±4.03 1,107 ±4 27.3% 2026-11-11 0106
LMArena text/hard_prompts 1,085 ±5.63 1,110 ±5 26.2% 2026-11-11 0106
LMArena text/instruction_following 1,076 ±5.31 1,106 ±5 13.2% 2026-11-11 0106
LMArena text/expert 1,052 ±12 1,110 ±10 10.4% 2026-11-11 0106
LMArena text/multi_turn 1,091 ±7.65 1,118 ±7 6.0% 2026-11-11 0106
LMArena text/longer_query 1,093 ±14 1,113 ±13 4.1% 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

D Coding 1,135 [1,124–1,146] Percentile 14 · #246 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,113 ±7.09 1,125 ±6 87.2% 2026-11-11 0106

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 Math 1,124 [1,112–1,135] Percentile 13 · #223 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,107 ±6.93 1,112 ±7 87.0% 2026-11-11 0106

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 1,144 [1,130–1,158] Percentile 18 · #216 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,125 ±9.15 1,148 ±9 65.9% 2026-11-11 —
LMArena text/longer_query 1,093 ±14 1,113 ±13 25.5% 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

D Language: 繁體中文 1,128 [1,116–1,141] Percentile 11 · #196 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,084 ±8.90 1,123 ±7 92.9% 2026-11-11 0106

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 1,110 [1,102–1,119] Percentile 15 · #228 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,131 ±4.47 1,104 ±5 93.6% 2026-11-11 0106

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
OpenChat 3.5 (0106) 1,121 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: OpenChat 3.5 (0106)

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