Skip to content
fedi.software

Llama 3.3 Nemotron Super 49B v1.5 in fedi-index

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

fedi-index · General

C 1,315 ±6

Percentile 37 · #185 · provisional

People prefer / Solves tasks

1,323 / —

Human votes vs benchmarks, Elo-eq

Value

-40

$0.40 per 1M tokens, median of 1 providers

On your hardware

Does not fit the reference setups.

Score decomposition

C General 1,315 [1,309–1,321] Percentile 37 · #185 · components: 5 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,338 ±5.11 1,338 ±5 32.2% 2026-10-02 —
LMArena text/hard_prompts 1,334 ±7.66 1,336 ±7 29.6% 2026-10-02 —
LMArena text/instruction_following 1,298 ±10 1,317 ±10 12.7% 2026-10-02 —
LMArena text/longer_query 1,313 ±11 1,320 ±10 6.1% 2026-10-02 —
LMArena text/multi_turn 1,334 ±12 1,339 ±11 5.8% 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 Coding 1,323 [1,306–1,340] Percentile 35 · #180 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,354 ±11 1,341 ±10 86.9% 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

C Writing 1,315 [1,298–1,332] Percentile 41 · #159 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,307 ±15 1,333 ±15 53.2% 2026-10-02 —
LMArena text/longer_query 1,313 ±11 1,320 ±10 36.6% 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 Language: English 1,333 [1,318–1,348] Percentile 41 · #162 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,358 ±7.70 1,344 ±8 92.5% 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

C Language: 日本語 1,339 [1,319–1,359] Percentile 27 · #94 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/japanese 1,301 ±15 1,352 ±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

D Language: Polski 1,329 [1,307–1,351] Percentile 12 · #116 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/polish 1,323 ±15 1,342 ±12 90.4% 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
Llama 3.3 Nemotron Super 49B v1.5 1,315 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 3.3 Nemotron Super 49B v1.5

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