Skip to content
fedi.software

Nemotron 3 Super in fedi-index

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

fedi-index · General

C 1,356 ±4

Percentile 49 · #149 · provisional

People prefer / Solves tasks

1,366 / —

Human votes vs benchmarks, Elo-eq

Value

+0

$0.40 per 1M tokens, median of 14 providers · vendor $0.35

On your hardware

  • GPU 12 GB #16 · Q3_K_M · ≈10 tok/s
  • GPU 24 GB #16 · Q3_K_M · ≈14 tok/s
  • Mac 64 GB #20 · Q2_K · strong compression · ≈41 tok/s
  • 128 GB unified memory #24 · Q6_K · ≈12 tok/s

Score decomposition

C General 1,356 [1,352–1,360] Percentile 49 · #149 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,378 ±3.60 1,378 ±4 26.8% 2026-10-02 —
LMArena text/hard_prompts 1,386 ±4.58 1,382 ±4 26.3% 2026-10-02 —
LMArena text/instruction_following 1,347 ±6.33 1,363 ±6 12.2% 2026-10-02 —
LMArena text/expert 1,397 ±11 1,392 ±9 10.3% 2026-10-02 —
LMArena text/longer_query 1,362 ±6.11 1,365 ±6 6.2% 2026-10-02 —
LMArena text/multi_turn 1,369 ±8.07 1,371 ±7 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

B Coding 1,365 [1,354–1,375] Percentile 50 · #139 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,403 ±6.72 1,384 ±6 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

C Math 1,346 [1,326–1,365] Percentile 45 · #141 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,381 ±12 1,375 ±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 1,340 [1,329–1,352] Percentile 46 · #144 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,317 ±8.95 1,344 ±9 57.9% 2026-10-02 —
LMArena text/longer_query 1,362 ±6.11 1,365 ±6 34.7% 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 Language: 繁體中文 1,382 [1,365–1,399] Percentile 48 · #116 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,430 ±12 1,397 ±9 92.0% 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

B Language: English 1,376 [1,366–1,386] Percentile 56 · #122 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,400 ±5.25 1,388 ±6 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

C Language: Español 1,392 [1,366–1,417] Percentile 43 · #85 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/spanish 1,418 ±16 1,415 ±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

C Language: Русский 1,338 [1,323–1,353] Percentile 37 · #147 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,336 ±9.23 1,349 ±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

History

fedi-index by month
The same in a table
Model 2026-10
Nemotron 3 Super 1,356 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: Nemotron 3 Super

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