Nemotron 3.5 Super VL 120B A12B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,381 ±5
Percentile 57 · #128 · provisional
People prefer / Solves tasks
1,394 / —
Human votes vs benchmarks, Elo-eq
Value
+47
$0.275 per 1M tokens, median of 12 providers
On your hardware
Does not fit the reference setups.
Score decomposition
B General 1,381 [1,376–1,386] Percentile 57 · #128 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,407 ±4.87 | 1,407 ±5 | 27.5% | 2026-11-11 | — |
| LMArena |
text/hard_prompts
|
1,414 ±6.12 | 1,408 ±6 | 26.7% | 2026-11-11 | — |
| LMArena |
text/instruction_following
|
1,400 ±8.32 | 1,413 ±8 | 11.9% | 2026-11-11 | — |
| LMArena |
text/expert
|
1,422 ±14 | 1,412 ±12 | 9.4% | 2026-11-11 | — |
| LMArena |
text/longer_query
|
1,396 ±7.52 | 1,397 ±7 | 6.2% | 2026-11-11 | — |
| LMArena |
text/multi_turn
|
1,415 ±12 | 1,413 ±11 | 4.9% | 2026-11-11 | — |
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 1,390 [1,383–1,396] Percentile 60 · #115 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,401 ±5.36 | 1,422 ±2 | 49.7% | 2026-11-15 | — |
| LMArena |
text/coding
|
1,433 ±9.71 | 1,410 ±9 | 37.7% | 2026-11-11 | — |
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 Agents 1,356 [1,353–1,359] Percentile 9 · #71 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.17 ±0.00 | 1,376 ±2 | 88.8% | 2026-11-15 | — |
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 Vision 1,386 [1,380–1,392] Percentile 36 · #71 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,214 ±4.75 | 1,398 ±4 | 64.2% | 2026-11-09 | — |
| LMArena |
vision/ocr
|
1,223 ±5.42 | 1,397 ±5 | 15.5% | 2026-11-09 | — |
| LMArena |
vision/diagram
|
1,233 ±8.55 | 1,404 ±8 | 13.8% | 2026-11-09 | — |
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 Writing 1,386 [1,373–1,399] Percentile 57 · #114 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,377 ±10 | 1,405 ±11 | 56.9% | 2026-11-11 | — |
| LMArena |
text/longer_query
|
1,396 ±7.52 | 1,397 ±7 | 35.1% | 2026-11-11 | — |
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 1,404 [1,389–1,419] Percentile 63 · #99 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,430 ±7.66 | 1,420 ±8 | 92.5% | 2026-11-11 | — |
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 1,364 [1,343–1,385] Percentile 42 · #135 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,370 ±13 | 1,380 ±12 | 90.8% | 2026-11-11 | — |
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 | 2026-11 |
|---|---|
| Nemotron 3.5 Super VL 120B A12B | 1,381 B |
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.