Skip to content
fedi.software

llama-3.1-tulu-3-8b in fedi-index

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

fedi-index · General

D 1,194 ±7

Percentile 22 · #228 · provisional

People prefer / Solves tasks

1,193 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,194 [1,187–1,200] Percentile 22 · #228 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,193 ±5.35 1,193 ±5 32.8% 2026-10-02 —
LMArena text/hard_prompts 1,174 ±9.98 1,191 ±9 27.2% 2026-10-02 —
LMArena text/instruction_following 1,174 ±7.87 1,199 ±8 14.8% 2026-10-02 —
LMArena text/multi_turn 1,154 ±13 1,175 ±12 5.8% 2026-10-02 —
LMArena text/longer_query 1,181 ±13 1,196 ±12 5.6% 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 Coding 1,190 [1,172–1,209] Percentile 21 · #220 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,183 ±12 1,188 ±11 86.2% 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 Math 1,197 [1,177–1,218] Percentile 24 · #195 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,195 ±13 1,196 ±12 82.6% 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 Writing 1,202 [1,185–1,219] Percentile 23 · #206 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,182 ±13 1,205 ±13 58.9% 2026-10-02 —
LMArena text/longer_query 1,181 ±13 1,196 ±12 31.4% 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 Language: English 1,193 [1,180–1,206] Percentile 25 · #206 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,215 ±6.94 1,192 ±7 92.8% 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

D Language: Русский 1,219 [1,199–1,239] Percentile 16 · #196 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,193 ±13 1,221 ±11 91.1% 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

History

fedi-index by month
The same in a table
Model 2026-10
llama-3.1-tulu-3-8b 1,194 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: llama-3.1-tulu-3-8b

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