nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,319 ±3
Percentile 39 · #180 · provisional
People prefer / Solves tasks
1,326 / —
Human votes vs benchmarks, Elo-eq
Value
+3
$0.0768 per 1M tokens, median of 2 providers
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,319 [1,316–1,322] Percentile 39 · #180 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,327 ±3.07 | 1,327 ±3 | 26.1% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,336 ±3.63 | 1,337 ±3 | 25.9% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,317 ±4.63 | 1,335 ±4 | 12.5% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,352 ±7.73 | 1,355 ±6 | 11.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,312 ±4.36 | 1,318 ±4 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,326 ±7.32 | 1,332 ±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
C Coding 1,340 [1,332–1,348] Percentile 39 · #169 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,371 ±5.22 | 1,356 ±5 | 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
C Math 1,326 [1,306–1,345] Percentile 37 · #160 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,356 ±12 | 1,351 ±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 1,287 [1,279–1,295] Percentile 34 · #177 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,253 ±6.16 | 1,279 ±6 | 60.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,312 ±4.36 | 1,318 ±4 | 33.0% | 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 Language: 繁體中文 1,331 [1,317–1,345] Percentile 34 · #147 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,359 ±9.57 | 1,341 ±8 | 92.7% | 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: English 1,337 [1,329–1,345] Percentile 42 · #158 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,360 ±4.16 | 1,346 ±4 | 93.6% | 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
D Language: Español 1,328 [1,304–1,353] Percentile 15 · #127 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,340 ±15 | 1,343 ±14 | 89.6% | 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
D Language: Français 1,341 [1,318–1,364] Percentile 19 · #110 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,367 ±15 | 1,356 ±13 | 90.0% | 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
D Language: Русский 1,274 [1,260–1,287] Percentile 25 · #176 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,258 ±8.09 | 1,279 ±7 | 92.8% | 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 |
|---|---|
| nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 | 1,319 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.