Skip to content
fedi.software

Llama 3.1 Nemotron 70B Instruct in fedi-index

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

fedi-index · General

C 1,266 ±5

Percentile 29 · #208 · provisional

People prefer / Solves tasks

1,270 / —

Human votes vs benchmarks, Elo-eq

Value

-95

$0.4849 per 1M tokens, median of 2 providers

On your hardware

Does not fit the reference setups.

Score decomposition

C General 1,266 [1,261–1,270] Percentile 29 · #208 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,283 ±3.93 1,283 ±4 27.5% 2026-10-02 —
LMArena text/hard_prompts 1,266 ±6.48 1,274 ±6 25.6% 2026-10-02 —
LMArena text/instruction_following 1,252 ±5.52 1,273 ±5 13.1% 2026-10-02 —
LMArena text/expert 1,242 ±14 1,266 ±11 9.5% 2026-10-02 —
LMArena text/multi_turn 1,275 ±8.50 1,286 ±8 5.8% 2026-10-02 —
LMArena text/longer_query 1,238 ±8.86 1,250 ±8 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

C Coding 1,260 [1,248–1,272] Percentile 28 · #199 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,272 ±7.78 1,267 ±7 88.8% 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 Math 1,260 [1,246–1,274] Percentile 31 · #177 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,271 ±8.61 1,269 ±8 86.0% 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 1,272 [1,260–1,285] Percentile 32 · #183 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,269 ±9.50 1,294 ±10 59.6% 2026-10-02 —
LMArena text/longer_query 1,238 ±8.86 1,250 ±8 32.4% 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: 繁體中文 1,260 [1,245–1,276] Percentile 24 · #170 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,263 ±11 1,265 ±9 92.3% 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: English 1,292 [1,282–1,302] Percentile 34 · #180 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,315 ±5.05 1,298 ±5 93.4% 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: Русский 1,248 [1,233–1,262] Percentile 20 · #187 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,227 ±8.80 1,251 ±8 92.6% 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

History

fedi-index by month
The same in a table
Model 2026-10
Llama 3.1 Nemotron 70B Instruct 1,266 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 Nemotron 70B Instruct

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