Llama 3.1 Nemotron Ultra 253B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,303 ±7
Percentile 36 · #189 · provisional
People prefer / Solves tasks
1,310 / —
Human votes vs benchmarks, Elo-eq
Value
Free
On your hardware
Does not fit the reference setups.
Score decomposition
C General 1,303 [1,295–1,310] Percentile 36 · #189 · components: 5 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,320 ±5.88 | 1,320 ±6 | 33.9% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,316 ±11 | 1,319 ±10 | 27.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,308 ±11 | 1,326 ±10 | 13.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,317 ±15 | 1,324 ±14 | 5.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,299 ±15 | 1,306 ±14 | 5.2% | 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 Coding 1,287 [1,265–1,309] Percentile 30 · #195 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,312 ±15 | 1,303 ±13 | 84.2% | 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 Writing 1,316 [1,298–1,334] Percentile 41 · #158 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,314 ±13 | 1,341 ±14 | 60.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,299 ±15 | 1,306 ±14 | 29.4% | 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 1,320 [1,306–1,335] Percentile 38 · #170 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,345 ±7.49 | 1,330 ±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
C Language: Русский 1,292 [1,268–1,316] Percentile 28 · #170 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,284 ±15 | 1,302 ±14 | 89.8% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Llama 3.1 Nemotron Ultra 253B | 1,303 C |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.