Skip to content
fedi.software

olmo-3.1-32b-instruct in fedi-index

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

fedi-index · General

C 1,304 ±3

Percentile 36 · #188 · provisional

People prefer / Solves tasks

1,310 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,304 [1,300–1,307] Percentile 36 · #188 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,311 ±3.11 1,311 ±3 26.7% 2026-10-02 —
LMArena text/hard_prompts 1,322 ±3.99 1,324 ±4 26.3% 2026-10-02 —
LMArena text/instruction_following 1,298 ±5.40 1,317 ±5 12.5% 2026-10-02 —
LMArena text/expert 1,307 ±11 1,319 ±9 10.2% 2026-10-02 —
LMArena text/longer_query 1,312 ±5.52 1,318 ±5 6.2% 2026-10-02 —
LMArena text/multi_turn 1,309 ±6.74 1,316 ±6 6.0% 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

C Coding 1,320 [1,310–1,329] Percentile 35 · #181 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,347 ±6.03 1,334 ±5 89.5% 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

C Math 1,286 [1,268–1,304] Percentile 34 · #170 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,305 ±12 1,302 ±11 83.8% 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

C Writing 1,293 [1,284–1,303] Percentile 36 · #173 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,264 ±7.52 1,290 ±8 59.4% 2026-10-02 —
LMArena text/longer_query 1,312 ±5.52 1,318 ±5 33.6% 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

C Language: 繁體中文 1,290 [1,275–1,305] Percentile 27 · #164 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,304 ±11 1,297 ±8 92.4% 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

C Language: English 1,330 [1,321–1,339] Percentile 40 · #165 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,353 ±4.52 1,339 ±5 93.6% 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: Español 1,325 [1,300–1,351] Percentile 14 · #128 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,337 ±16 1,340 ±14 89.2% 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 Language: Français 1,307 [1,278–1,335] Percentile 13 · #117 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/french 1,328 ±18 1,321 ±16 87.9% 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: Polski 1,250 [1,225–1,275] Percentile 0 · #131 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,221 ±17 1,256 ±14 89.3% 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

C Language: Русский 1,282 [1,270–1,294] Percentile 26 · #174 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,268 ±7.48 1,288 ±7 93.0% 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

History

fedi-index by month
The same in a table
Model 2026-10
olmo-3.1-32b-instruct 1,304 C

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-3.1-32b-instruct

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