Skip to content
fedi.software

Code Llama 34B Instruct in fedi-index

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

fedi-index · General

D 1,080 ±5

Percentile 8 · #273 · provisional

People prefer / Solves tasks

1,071 / —

Human votes vs benchmarks, Elo-eq

Value

—

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,080 [1,074–1,085] Percentile 8 · #273 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,066 ±4.47 1,066 ±4 32.0% 2026-11-11 —
LMArena text/hard_prompts 1,032 ±7.41 1,062 ±7 29.1% 2026-11-11 —
LMArena text/instruction_following 1,028 ±6.52 1,060 ±6 14.9% 2026-11-11 —
LMArena text/multi_turn 1,015 ±9.37 1,050 ±8 6.6% 2026-11-11 —
LMArena text/longer_query 1,013 ±17 1,039 ±16 4.2% 2026-11-11 —

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 1,086 [1,070–1,101] Percentile 8 · #264 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,046 ±10 1,065 ±9 85.4% 2026-11-11 —

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 1,084 [1,068–1,100] Percentile 8 · #235 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,056 ±9.76 1,064 ±9 85.2% 2026-11-11 —

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 1,062 [1,048–1,076] Percentile 8 · #243 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,031 ±8.47 1,052 ±9 69.0% 2026-11-11 —
LMArena text/longer_query 1,013 ±17 1,039 ±16 22.3% 2026-11-11 —

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 1,072 [1,062–1,081] Percentile 9 · #245 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,092 ±4.92 1,063 ±5 93.5% 2026-11-11 —

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 2026-11
Code Llama 34B Instruct 1,080 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: Code Llama 34B Instruct

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