Skip to content
fedi.software

llama-3.1-tulu-3-70b in fedi-index

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

fedi-index · General

C 1,241 ±6

Percentile 27 · #213 · provisional

People prefer / Solves tasks

1,244 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

C General 1,241 [1,235–1,248] Percentile 27 · #213 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,256 ±5.33 1,256 ±5 32.4% 2026-10-02 —
LMArena text/hard_prompts 1,220 ±9.41 1,232 ±8 27.6% 2026-10-02 —
LMArena text/instruction_following 1,233 ±7.88 1,254 ±8 14.6% 2026-10-02 —
LMArena text/multi_turn 1,252 ±12 1,264 ±11 6.0% 2026-10-02 —
LMArena text/longer_query 1,224 ±13 1,236 ±12 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

C Coding 1,230 [1,212–1,248] Percentile 25 · #208 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,235 ±12 1,235 ±11 86.4% 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 Math 1,235 [1,215–1,254] Percentile 28 · #184 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,242 ±12 1,242 ±12 83.0% 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 Writing 1,245 [1,228–1,261] Percentile 29 · #190 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,231 ±12 1,256 ±13 59.0% 2026-10-02 —
LMArena text/longer_query 1,224 ±13 1,236 ±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

C Language: English 1,250 [1,237–1,263] Percentile 29 · #193 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,273 ±6.77 1,254 ±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 1,262 [1,240–1,284] Percentile 23 · #181 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,246 ±14 1,268 ±12 90.5% 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

History

fedi-index by month
The same in a table
Model 2026-10
llama-3.1-tulu-3-70b 1,241 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: llama-3.1-tulu-3-70b

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