Skip to content
fedi.software

Ember-1 in fedi-index

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

fedi-index · General

B 1,375 ±5

Percentile 52 · #137 · provisional

People prefer / Solves tasks

— / 1,402

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

B Coding 1,375 [1,370–1,380] Percentile 52 · #137 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
Terminal-Bench tbench/terminal-bench decay ×0.90 0.22 ±0.02 1,438 ±4 73.3% 2026-09-24 —

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 1,375 [1,370–1,380] Percentile 17 · #65 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
Terminal-Bench tbench/terminal-bench decay ×0.90 0.22 ±0.02 1,438 ±4 73.3% 2026-09-24 —

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

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: Ember-1

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