Skip to content
fedi.software

olmo-7b-instruct in fedi-index

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

fedi-index · General

D 1,051 ±7

Percentile 4 · #281 · provisional

People prefer / Solves tasks

1,040 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,051 [1,044–1,058] Percentile 4 · #281 · components: 4 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,032 ±5.63 1,032 ±6 34.3% 2026-10-02 —
LMArena text/hard_prompts 993 ±8.50 1,027 ±8 31.0% 2026-10-02 —
LMArena text/instruction_following 978 ±8.00 1,014 ±8 15.6% 2026-10-02 —
LMArena text/multi_turn 1,007 ±14 1,042 ±13 5.7% 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 1,060 [1,043–1,077] Percentile 5 · #265 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,016 ±11 1,039 ±10 87.0% 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 Math 1,052 [1,037–1,068] Percentile 4 · #245 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,018 ±9.69 1,026 ±9 85.2% 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 1,026 [1,007–1,044] Percentile 4 · #258 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 990 ±10 1,009 ±10 91.5% 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 1,078 [1,061–1,095] Percentile 3 · #216 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,013 ±12 1,067 ±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 1,048 [1,035–1,060] Percentile 6 · #258 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,067 ±6.59 1,036 ±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 1,019 [996–1,042] Percentile 0 · #234 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 946 ±14 999 ±13 90.3% 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
olmo-7b-instruct 1,051 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: olmo-7b-instruct

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