Skip to content
fedi.software

zephyr-orpo-141b-A35b-v0.1 in fedi-index

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

fedi-index · General

D 1,148 ±6

Percentile 18 · #240 · provisional

People prefer / Solves tasks

1,144 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,148 [1,142–1,155] Percentile 18 · #240 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,144 ±5.47 1,144 ±6 32.0% 2026-10-02 —
LMArena text/hard_prompts 1,116 ±8.46 1,138 ±8 28.8% 2026-10-02 —
LMArena text/instruction_following 1,118 ±7.85 1,146 ±7 14.6% 2026-10-02 —
LMArena text/multi_turn 1,100 ±12 1,126 ±11 5.9% 2026-10-02 —
LMArena text/longer_query 1,105 ±14 1,125 ±13 5.1% 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

D Coding 1,148 [1,132–1,164] Percentile 16 · #234 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,129 ±10 1,140 ±9 87.4% 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

D Math 1,159 [1,142–1,177] Percentile 17 · #212 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,148 ±11 1,151 ±11 84.0% 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

D Writing 1,139 [1,122–1,155] Percentile 18 · #220 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,113 ±12 1,135 ±12 61.9% 2026-10-02 —
LMArena text/longer_query 1,105 ±14 1,125 ±13 28.6% 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

D Language: 繁體中文 1,128 [1,111–1,145] Percentile 10 · #201 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,082 ±12 1,121 ±9 92.0% 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

D Language: English 1,154 [1,141–1,166] Percentile 21 · #217 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,174 ±6.71 1,150 ±7 92.9% 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 Language: Русский 1,156 [1,134–1,178] Percentile 11 · #208 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,116 ±14 1,151 ±12 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
zephyr-orpo-141b-A35b-v0.1 1,148 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: zephyr-orpo-141b-A35b-v0.1

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